Training in progress, step 340000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54534335b10706006d453ec56a979a5d5c461f57d0f68d1a6ad0a77c57a0aecf
+oid sha256:a70f0de01be5fcc7537de81ac336cef4498cd2899bb7ea7761980f3fb9003a0f
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea75c11d2eaacb0e2bbd235a00be3c1d10c576c2381b03ccce251e6969bea54
+oid sha256:20cd52574261829d86d2a5ad2e1ec4588da3ef0a45a350a2067e301217ba680c
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
+oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
+oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
+oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
+oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
+oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
+oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
+oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
+oid sha256:2338329382f06f686ee9c5eb07d6fdd675982256722ac66aa8cd97d96a331441
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636cb28fce30ad56f68aface20193360fd815697da4c2ec39f5ca647b5e6b45b
+oid sha256:4a0f100ea6da4a9ff03fc2cc9b0cbbba13b42ccc41293a1d6143e5a081a97f70
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.410214587899485,
-  "global_step": 330000,
+  "epoch": 8.665069575411591,
+  "global_step": 340000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6606,11 +6606,211 @@
       "eval_samples_per_second": 803.539,
       "eval_steps_per_second": 12.857,
       "step": 330000
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 9.196345158526793e-05,
+      "loss": 0.2786,
+      "step": 330500
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 9.153197361721149e-05,
+      "loss": 0.2792,
+      "step": 331000
+    },
+    {
+      "epoch": 8.44,
+      "eval_loss": 0.8179449439048767,
+      "eval_runtime": 1.254,
+      "eval_samples_per_second": 797.474,
+      "eval_steps_per_second": 12.76,
+      "step": 331000
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 9.110118972532302e-05,
+      "loss": 0.2788,
+      "step": 331500
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 9.067110462058634e-05,
+      "loss": 0.2788,
+      "step": 332000
+    },
+    {
+      "epoch": 8.46,
+      "eval_loss": 0.8141337633132935,
+      "eval_runtime": 1.3186,
+      "eval_samples_per_second": 758.376,
+      "eval_steps_per_second": 12.134,
+      "step": 332000
+    },
+    {
+      "epoch": 8.47,
+      "learning_rate": 9.024172300634305e-05,
+      "loss": 0.2789,
+      "step": 332500
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 8.981304957824182e-05,
+      "loss": 0.2785,
+      "step": 333000
+    },
+    {
+      "epoch": 8.49,
+      "eval_loss": 0.8111985325813293,
+      "eval_runtime": 1.2328,
+      "eval_samples_per_second": 811.183,
+      "eval_steps_per_second": 12.979,
+      "step": 333000
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 8.938508902418643e-05,
+      "loss": 0.2786,
+      "step": 333500
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 8.89578460242851e-05,
+      "loss": 0.2786,
+      "step": 334000
+    },
+    {
+      "epoch": 8.51,
+      "eval_loss": 0.8080055117607117,
+      "eval_runtime": 1.2558,
+      "eval_samples_per_second": 796.279,
+      "eval_steps_per_second": 12.74,
+      "step": 334000
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 8.85313252507988e-05,
+      "loss": 0.2785,
+      "step": 334500
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 8.810553136809027e-05,
+      "loss": 0.2788,
+      "step": 335000
+    },
+    {
+      "epoch": 8.54,
+      "eval_loss": 0.8105797171592712,
+      "eval_runtime": 1.2508,
+      "eval_samples_per_second": 799.461,
+      "eval_steps_per_second": 12.791,
+      "step": 335000
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 8.76804690325733e-05,
+      "loss": 0.2792,
+      "step": 335500
+    },
+    {
+      "epoch": 8.56,
+      "learning_rate": 8.725614289266137e-05,
+      "loss": 0.279,
+      "step": 336000
+    },
+    {
+      "epoch": 8.56,
+      "eval_loss": 0.8105652928352356,
+      "eval_runtime": 1.5015,
+      "eval_samples_per_second": 666.004,
+      "eval_steps_per_second": 10.656,
+      "step": 336000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 8.683255758871734e-05,
+      "loss": 0.2782,
+      "step": 336500
+    },
+    {
+      "epoch": 8.59,
+      "learning_rate": 8.640971775300207e-05,
+      "loss": 0.2781,
+      "step": 337000
+    },
+    {
+      "epoch": 8.59,
+      "eval_loss": 0.8099997043609619,
+      "eval_runtime": 1.3182,
+      "eval_samples_per_second": 758.589,
+      "eval_steps_per_second": 12.137,
+      "step": 337000
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 8.598762800962431e-05,
+      "loss": 0.2779,
+      "step": 337500
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 8.55662929744899e-05,
+      "loss": 0.278,
+      "step": 338000
+    },
+    {
+      "epoch": 8.61,
+      "eval_loss": 0.8251625895500183,
+      "eval_runtime": 1.3504,
+      "eval_samples_per_second": 740.537,
+      "eval_steps_per_second": 11.849,
+      "step": 338000
+    },
+    {
+      "epoch": 8.63,
+      "learning_rate": 8.514571725525124e-05,
+      "loss": 0.2778,
+      "step": 338500
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 8.47259054512571e-05,
+      "loss": 0.2777,
+      "step": 339000
+    },
+    {
+      "epoch": 8.64,
+      "eval_loss": 0.8137243390083313,
+      "eval_runtime": 1.2434,
+      "eval_samples_per_second": 804.259,
+      "eval_steps_per_second": 12.868,
+      "step": 339000
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 8.430686215350198e-05,
+      "loss": 0.2777,
+      "step": 339500
+    },
+    {
+      "epoch": 8.67,
+      "learning_rate": 8.388859194457636e-05,
+      "loss": 0.2778,
+      "step": 340000
+    },
+    {
+      "epoch": 8.67,
+      "eval_loss": 0.8186727166175842,
+      "eval_runtime": 1.2904,
+      "eval_samples_per_second": 774.959,
+      "eval_steps_per_second": 12.399,
+      "step": 340000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.054296774825414e+22,
+  "total_flos": 1.086245488702864e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea75c11d2eaacb0e2bbd235a00be3c1d10c576c2381b03ccce251e6969bea54
+oid sha256:20cd52574261829d86d2a5ad2e1ec4588da3ef0a45a350a2067e301217ba680c
 size 102501541