Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f78dbb041bde2e76fb127ebdd1f1b07bd8f66440939bb8a9027caa7c7290cfd0
+oid sha256:62332de7696193cf95c4b58f4eb71109e913e5eb2307c4eb5d6049395383233d
 size 363365712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc0a6d8254dc78f9d2b5f2abe3ca5bc8d71a742f273b994b15e84027e44e401
+oid sha256:4b3a7e528d79a9b026ad94e82546d4dd18bf55086ba1a8f27ea25d5ccc064e43
 size 184804245

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a1ced4462bf42ecbfb4907fdd784be4250f55d7914098378605e799a2694bd
+oid sha256:c90bdde377afa379e25942974e4de5693c679ed32584e381f0995f3b231e8b71
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063687fa98a284945d31c40fd5b274f6ad27c3589a63e05ef46849dead15e268
+oid sha256:833953e669cbb5eb96748291f5173e6f08a3adcb454e0306bb8141ba9e5d2b71
 size 14917

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
+oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8939a4d5ae844310d52e090956d7cd114317d0e7c8aac0bc209cd61d5f12cb
+oid sha256:dfeb39df0143fba24e4d36209079730a02d1b954efa1d4d7185a519ce59f98de
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.851063829787234,
+  "epoch": 1.2765957446808511,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -408,6 +408,206 @@
       "mean_token_accuracy": 0.6744833959639073,
       "num_tokens": 39440483.0,
       "step": 2000
+    },
+    {
+      "entropy": 1.764250594675541,
+      "epoch": 0.8723404255319149,
+      "grad_norm": 0.7506063580513,
+      "learning_rate": 7.951e-05,
+      "loss": 1.7482571411132812,
+      "mean_token_accuracy": 0.6752947215735913,
+      "num_tokens": 40425735.0,
+      "step": 2050
+    },
+    {
+      "entropy": 1.7635737213492393,
+      "epoch": 0.8936170212765957,
+      "grad_norm": 0.7649574279785156,
+      "learning_rate": 7.901e-05,
+      "loss": 1.7502963256835937,
+      "mean_token_accuracy": 0.6766997446119786,
+      "num_tokens": 41416623.0,
+      "step": 2100
+    },
+    {
+      "entropy": 1.7378215923905374,
+      "epoch": 0.9148936170212766,
+      "grad_norm": 0.7321686744689941,
+      "learning_rate": 7.851e-05,
+      "loss": 1.7229681396484375,
+      "mean_token_accuracy": 0.6783718758821488,
+      "num_tokens": 42407921.0,
+      "step": 2150
+    },
+    {
+      "entropy": 1.720134773850441,
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.7562823295593262,
+      "learning_rate": 7.801000000000001e-05,
+      "loss": 1.7002345275878907,
+      "mean_token_accuracy": 0.6815671770274639,
+      "num_tokens": 43394397.0,
+      "step": 2200
+    },
+    {
+      "entropy": 1.7291932779550552,
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.746076762676239,
+      "learning_rate": 7.751000000000001e-05,
+      "loss": 1.7090219116210938,
+      "mean_token_accuracy": 0.6812707696855068,
+      "num_tokens": 44375854.0,
+      "step": 2250
+    },
+    {
+      "entropy": 1.720713329911232,
+      "epoch": 0.9787234042553191,
+      "grad_norm": 0.770660936832428,
+      "learning_rate": 7.701000000000001e-05,
+      "loss": 1.7028382873535157,
+      "mean_token_accuracy": 0.6824209858477116,
+      "num_tokens": 45371344.0,
+      "step": 2300
+    },
+    {
+      "entropy": 1.6982364651560784,
+      "epoch": 1.0,
+      "grad_norm": 0.7889444828033447,
+      "learning_rate": 7.651e-05,
+      "loss": 1.6777915954589844,
+      "mean_token_accuracy": 0.6852045242488384,
+      "num_tokens": 46351878.0,
+      "step": 2350
+    },
+    {
+      "entropy": 1.6709844982624054,
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.7106631398200989,
+      "learning_rate": 7.601e-05,
+      "loss": 1.6406138610839844,
+      "mean_token_accuracy": 0.6904737217724324,
+      "num_tokens": 47341427.0,
+      "step": 2400
+    },
+    {
+      "entropy": 1.6589670392870903,
+      "epoch": 1.0425531914893618,
+      "grad_norm": 0.7608166933059692,
+      "learning_rate": 7.551e-05,
+      "loss": 1.6304428100585937,
+      "mean_token_accuracy": 0.6913493700325489,
+      "num_tokens": 48322894.0,
+      "step": 2450
+    },
+    {
+      "entropy": 1.6474245920777322,
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.7659543752670288,
+      "learning_rate": 7.501e-05,
+      "loss": 1.6174127197265624,
+      "mean_token_accuracy": 0.693988469094038,
+      "num_tokens": 49309778.0,
+      "step": 2500
+    },
+    {
+      "entropy": 1.625294875204563,
+      "epoch": 1.0851063829787233,
+      "grad_norm": 0.7219650745391846,
+      "learning_rate": 7.451e-05,
+      "loss": 1.5934686279296875,
+      "mean_token_accuracy": 0.6972348481416702,
+      "num_tokens": 50292124.0,
+      "step": 2550
+    },
+    {
+      "entropy": 1.6406617045402527,
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.7679393291473389,
+      "learning_rate": 7.401e-05,
+      "loss": 1.6113711547851564,
+      "mean_token_accuracy": 0.6941907967627049,
+      "num_tokens": 51269742.0,
+      "step": 2600
+    },
+    {
+      "entropy": 1.6265540924668311,
+      "epoch": 1.127659574468085,
+      "grad_norm": 0.7457160949707031,
+      "learning_rate": 7.351e-05,
+      "loss": 1.600107421875,
+      "mean_token_accuracy": 0.6962076690793038,
+      "num_tokens": 52262686.0,
+      "step": 2650
+    },
+    {
+      "entropy": 1.6291374132037162,
+      "epoch": 1.148936170212766,
+      "grad_norm": 0.8142237067222595,
+      "learning_rate": 7.301e-05,
+      "loss": 1.5976341247558594,
+      "mean_token_accuracy": 0.695648788511753,
+      "num_tokens": 53248843.0,
+      "step": 2700
+    },
+    {
+      "entropy": 1.6227850529551506,
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.7628965377807617,
+      "learning_rate": 7.251e-05,
+      "loss": 1.5930337524414062,
+      "mean_token_accuracy": 0.6979775196313858,
+      "num_tokens": 54241409.0,
+      "step": 2750
+    },
+    {
+      "entropy": 1.6028004956245423,
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.7493979334831238,
+      "learning_rate": 7.201e-05,
+      "loss": 1.5724569702148437,
+      "mean_token_accuracy": 0.6999971604347229,
+      "num_tokens": 55231488.0,
+      "step": 2800
+    },
+    {
+      "entropy": 1.616425441801548,
+      "epoch": 1.2127659574468086,
+      "grad_norm": 0.7527705430984497,
+      "learning_rate": 7.151e-05,
+      "loss": 1.5838508605957031,
+      "mean_token_accuracy": 0.6987825597822667,
+      "num_tokens": 56214657.0,
+      "step": 2850
+    },
+    {
+      "entropy": 1.6064529752731322,
+      "epoch": 1.2340425531914894,
+      "grad_norm": 0.744288444519043,
+      "learning_rate": 7.101e-05,
+      "loss": 1.5755838012695313,
+      "mean_token_accuracy": 0.6994880273938179,
+      "num_tokens": 57199159.0,
+      "step": 2900
+    },
+    {
+      "entropy": 1.5955200618505478,
+      "epoch": 1.2553191489361701,
+      "grad_norm": 0.7527694702148438,
+      "learning_rate": 7.051e-05,
+      "loss": 1.5658992004394532,
+      "mean_token_accuracy": 0.701285338550806,
+      "num_tokens": 58173001.0,
+      "step": 2950
+    },
+    {
+      "entropy": 1.5903715097904205,
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.7520326972007751,
+      "learning_rate": 7.001e-05,
+      "loss": 1.5549607849121094,
+      "mean_token_accuracy": 0.701934365928173,
+      "num_tokens": 59164486.0,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -427,7 +627,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9966095701612954e+17,
+  "total_flos": 4.496366043450573e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null