Training in progress, step 32000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a06d3e4983c41dc765c1eeb6d6658168972c5471a58499281b23d7c94887016
+oid sha256:e13225a7520c413144c7c1c355420a5c229ae4cb9ee2fc3ee9e6ec481a263534
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de60ec340a338ae4512a57938b518f19425ddce90de24fb45b35add85e7ffcf
+oid sha256:bc20992a7d2218d1b0875c85fb7d66067b2298850958dd0d9986500e15e7e571
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a55af3df2d414ccfff007ed59f001ee92e87d61217a24dace06b2b7ddba80fa
+oid sha256:77b2a9c9cdb925b9023364da46617175730aa23d1c7044261e0928c3c8b3fa89
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab5189814d428569ba62b550ae72cffeac88caf85e39082cf01ca7e7f9f982e
+oid sha256:39126e57e188afe7385c7c1c99d9aefd09279fe89a89d601c31fe9b0f88441d3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
+  "epoch": 0.64,
   "eval_steps": 1000,
-  "global_step": 30000,
+  "global_step": 32000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2378,6 +2378,164 @@
       "eval_samples_per_second": 83.713,
       "eval_steps_per_second": 0.67,
       "step": 30000
+    },
+    {
+      "epoch": 0.602,
+      "grad_norm": 0.19772815704345703,
+      "learning_rate": 0.0007481724391727628,
+      "loss": 3.3089,
+      "step": 30100
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 0.16669701039791107,
+      "learning_rate": 0.0007417772657395325,
+      "loss": 3.3032,
+      "step": 30200
+    },
+    {
+      "epoch": 0.606,
+      "grad_norm": 0.15029844641685486,
+      "learning_rate": 0.0007353933878052245,
+      "loss": 3.2961,
+      "step": 30300
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.1436147391796112,
+      "learning_rate": 0.0007290210846213408,
+      "loss": 3.2984,
+      "step": 30400
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.1456470638513565,
+      "learning_rate": 0.0007226606349330653,
+      "loss": 3.3059,
+      "step": 30500
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 0.15387193858623505,
+      "learning_rate": 0.0007163123169670729,
+      "loss": 3.3034,
+      "step": 30600
+    },
+    {
+      "epoch": 0.614,
+      "grad_norm": 0.1466827392578125,
+      "learning_rate": 0.0007099764084193565,
+      "loss": 3.278,
+      "step": 30700
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.17281971871852875,
+      "learning_rate": 0.0007036531864430824,
+      "loss": 3.2818,
+      "step": 30800
+    },
+    {
+      "epoch": 0.618,
+      "grad_norm": 0.15874525904655457,
+      "learning_rate": 0.0006973429276364641,
+      "loss": 3.3064,
+      "step": 30900
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.14938025176525116,
+      "learning_rate": 0.0006910459080306636,
+      "loss": 3.2793,
+      "step": 31000
+    },
+    {
+      "epoch": 0.62,
+      "eval_accuracy": 0.3857945205479452,
+      "eval_loss": 3.2896742820739746,
+      "eval_runtime": 12.6346,
+      "eval_samples_per_second": 79.148,
+      "eval_steps_per_second": 0.633,
+      "step": 31000
+    },
+    {
+      "epoch": 0.622,
+      "grad_norm": 0.12781454622745514,
+      "learning_rate": 0.0006847624030777184,
+      "loss": 3.2855,
+      "step": 31100
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.15578420460224152,
+      "learning_rate": 0.0006784926876384907,
+      "loss": 3.2931,
+      "step": 31200
+    },
+    {
+      "epoch": 0.626,
+      "grad_norm": 0.1583343893289566,
+      "learning_rate": 0.000672237035970645,
+      "loss": 3.283,
+      "step": 31300
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 0.14310809969902039,
+      "learning_rate": 0.0006659957217166504,
+      "loss": 3.2721,
+      "step": 31400
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.19646517932415009,
+      "learning_rate": 0.0006597690178918121,
+      "loss": 3.2853,
+      "step": 31500
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.1555543690919876,
+      "learning_rate": 0.0006535571968723266,
+      "loss": 3.2907,
+      "step": 31600
+    },
+    {
+      "epoch": 0.634,
+      "grad_norm": 0.15089106559753418,
+      "learning_rate": 0.0006473605303833691,
+      "loss": 3.2856,
+      "step": 31700
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 0.15569235384464264,
+      "learning_rate": 0.000641179289487206,
+      "loss": 3.268,
+      "step": 31800
+    },
+    {
+      "epoch": 0.638,
+      "grad_norm": 0.15568938851356506,
+      "learning_rate": 0.0006350137445713386,
+      "loss": 3.2885,
+      "step": 31900
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.14168080687522888,
+      "learning_rate": 0.0006288641653366752,
+      "loss": 3.2906,
+      "step": 32000
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.38636986301369863,
+      "eval_loss": 3.280740976333618,
+      "eval_runtime": 12.2058,
+      "eval_samples_per_second": 81.928,
+      "eval_steps_per_second": 0.655,
+      "step": 32000
     }
   ],
   "logging_steps": 100,