Training in progress, step 400000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed13a0abd470de3e8ade4fd2c5a55e9b3ebd6b4ed51afdc09a38bc8953462590
+oid sha256:95b2af8d25fdc6f0716a4799ff68a7e6fad43837a3cf29a819a852c15c29ffd3
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38fda9faa2af7932f137bd949d500e94c5a7ea45b10b762c9e46344a73cba8b9
+oid sha256:a9380afab6a0e5cafc287ef33a3ea44ed3cfb634c4d23234fce007fb6384cd9f
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a7dd626d6226ed58065304b2ea527ed577bb3bf1d26099838b84b34a9303f8
+oid sha256:7ed92842eb5c851b066e880a0c368aba9fc8dd7debf25e15b7dda51027cd22a7
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a7dd626d6226ed58065304b2ea527ed577bb3bf1d26099838b84b34a9303f8
+oid sha256:7ed92842eb5c851b066e880a0c368aba9fc8dd7debf25e15b7dda51027cd22a7
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a7dd626d6226ed58065304b2ea527ed577bb3bf1d26099838b84b34a9303f8
+oid sha256:7ed92842eb5c851b066e880a0c368aba9fc8dd7debf25e15b7dda51027cd22a7
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a7dd626d6226ed58065304b2ea527ed577bb3bf1d26099838b84b34a9303f8
+oid sha256:7ed92842eb5c851b066e880a0c368aba9fc8dd7debf25e15b7dda51027cd22a7
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a7dd626d6226ed58065304b2ea527ed577bb3bf1d26099838b84b34a9303f8
+oid sha256:7ed92842eb5c851b066e880a0c368aba9fc8dd7debf25e15b7dda51027cd22a7
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a7dd626d6226ed58065304b2ea527ed577bb3bf1d26099838b84b34a9303f8
+oid sha256:7ed92842eb5c851b066e880a0c368aba9fc8dd7debf25e15b7dda51027cd22a7
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a7dd626d6226ed58065304b2ea527ed577bb3bf1d26099838b84b34a9303f8
+oid sha256:7ed92842eb5c851b066e880a0c368aba9fc8dd7debf25e15b7dda51027cd22a7
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a7dd626d6226ed58065304b2ea527ed577bb3bf1d26099838b84b34a9303f8
+oid sha256:7ed92842eb5c851b066e880a0c368aba9fc8dd7debf25e15b7dda51027cd22a7
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864647684ab3694f7aa2a258c1806e10c4abf99f67ed5e54443050e485ac9436
+oid sha256:7ba83cbca80cb672828600b248dd69c4c050beb355cdcf7faf0b56212421edca
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.69914346895075,
-  "global_step": 390000,
+  "epoch": 8.922198429693076,
+  "global_step": 400000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7806,11 +7806,211 @@
       "eval_samples_per_second": 1166.029,
       "eval_steps_per_second": 18.275,
       "step": 390000
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 4.639259509788768e-05,
+      "loss": 0.26,
+      "step": 390500
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 4.60754920716572e-05,
+      "loss": 0.259,
+      "step": 391000
+    },
+    {
+      "epoch": 8.72,
+      "eval_loss": 0.2440621256828308,
+      "eval_runtime": 2.0127,
+      "eval_samples_per_second": 1141.226,
+      "eval_steps_per_second": 17.886,
+      "step": 391000
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 4.5759580226394167e-05,
+      "loss": 0.2593,
+      "step": 391500
+    },
+    {
+      "epoch": 8.74,
+      "learning_rate": 4.544486301685993e-05,
+      "loss": 0.2594,
+      "step": 392000
+    },
+    {
+      "epoch": 8.74,
+      "eval_loss": 0.23992255330085754,
+      "eval_runtime": 1.971,
+      "eval_samples_per_second": 1165.424,
+      "eval_steps_per_second": 18.265,
+      "step": 392000
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 4.5131343884751484e-05,
+      "loss": 0.2591,
+      "step": 392500
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 4.4819026258663774e-05,
+      "loss": 0.2591,
+      "step": 393000
+    },
+    {
+      "epoch": 8.77,
+      "eval_loss": 0.2458277940750122,
+      "eval_runtime": 1.9966,
+      "eval_samples_per_second": 1150.457,
+      "eval_steps_per_second": 18.031,
+      "step": 393000
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 4.450791355405234e-05,
+      "loss": 0.2592,
+      "step": 393500
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 4.419800917319588e-05,
+      "loss": 0.2591,
+      "step": 394000
+    },
+    {
+      "epoch": 8.79,
+      "eval_loss": 0.2452658861875534,
+      "eval_runtime": 1.9635,
+      "eval_samples_per_second": 1169.821,
+      "eval_steps_per_second": 18.334,
+      "step": 394000
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 4.3889316505159056e-05,
+      "loss": 0.2601,
+      "step": 394500
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 4.3581838925755465e-05,
+      "loss": 0.2591,
+      "step": 395000
+    },
+    {
+      "epoch": 8.81,
+      "eval_loss": 0.24037905037403107,
+      "eval_runtime": 2.0778,
+      "eval_samples_per_second": 1105.5,
+      "eval_steps_per_second": 17.326,
+      "step": 395000
+    },
+    {
+      "epoch": 8.82,
+      "learning_rate": 4.327557979751057e-05,
+      "loss": 0.2589,
+      "step": 395500
+    },
+    {
+      "epoch": 8.83,
+      "learning_rate": 4.297054246962517e-05,
+      "loss": 0.259,
+      "step": 396000
+    },
+    {
+      "epoch": 8.83,
+      "eval_loss": 0.2426002323627472,
+      "eval_runtime": 1.9871,
+      "eval_samples_per_second": 1155.977,
+      "eval_steps_per_second": 18.117,
+      "step": 396000
+    },
+    {
+      "epoch": 8.84,
+      "learning_rate": 4.266673027793864e-05,
+      "loss": 0.2583,
+      "step": 396500
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 4.236414654489242e-05,
+      "loss": 0.2583,
+      "step": 397000
+    },
+    {
+      "epoch": 8.86,
+      "eval_loss": 0.24136394262313843,
+      "eval_runtime": 2.043,
+      "eval_samples_per_second": 1124.309,
+      "eval_steps_per_second": 17.621,
+      "step": 397000
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 4.206279457949371e-05,
+      "loss": 0.2581,
+      "step": 397500
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 4.1762677677279335e-05,
+      "loss": 0.2584,
+      "step": 398000
+    },
+    {
+      "epoch": 8.88,
+      "eval_loss": 0.24172720313072205,
+      "eval_runtime": 1.9971,
+      "eval_samples_per_second": 1150.177,
+      "eval_steps_per_second": 18.026,
+      "step": 398000
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 4.146379912027964e-05,
+      "loss": 0.2582,
+      "step": 398500
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 4.1166162176982664e-05,
+      "loss": 0.2584,
+      "step": 399000
+    },
+    {
+      "epoch": 8.9,
+      "eval_loss": 0.2435595542192459,
+      "eval_runtime": 2.0606,
+      "eval_samples_per_second": 1114.743,
+      "eval_steps_per_second": 17.471,
+      "step": 399000
+    },
+    {
+      "epoch": 8.91,
+      "learning_rate": 4.086977010229838e-05,
+      "loss": 0.2583,
+      "step": 399500
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 4.057462613752294e-05,
+      "loss": 0.2615,
+      "step": 400000
+    },
+    {
+      "epoch": 8.92,
+      "eval_loss": 0.24273519217967987,
+      "eval_runtime": 1.9831,
+      "eval_samples_per_second": 1158.313,
+      "eval_steps_per_second": 18.154,
+      "step": 400000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.2459770778114178e+22,
+  "total_flos": 1.2779257916888678e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38fda9faa2af7932f137bd949d500e94c5a7ea45b10b762c9e46344a73cba8b9
+oid sha256:a9380afab6a0e5cafc287ef33a3ea44ed3cfb634c4d23234fce007fb6384cd9f
 size 102501541