Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd2ce83fb862336b4729018afc8e291aa4c2d38ce3b3b5625756b6a68e191913
+oid sha256:0dd24ee6828501b624fa6d66fd1194cee27acdf6fbf4040fa3393ed025f1e0b8
 size 174663600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4a1c0542d95372b9b98cd04e9e19b1d3278913800f038cdb84306140c9e0f5
+oid sha256:57c4a4dab1575e19036cc179b540af28afc954075c76fa1c3f74f467b18a0a54
 size 177908997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b03751160f25dd1f7c08604bdbd7711f070d950dfb96d9acede0b0ccf333222
+oid sha256:04eefe07496c9ea6eacb03b570d4b4b5896211d650c0810a1180d502bea3bcc3
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9803335b183336349e91b866e4b2332f37cecb5e5bd9cf6a14b120c0067b5d71
+oid sha256:119c8b8031efeada1dd54137e4c5ca8dc90f054b53a8f73cacb65b1b4acc4f58
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4724223455769458,
+  "epoch": 0.7086335183654187,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -408,6 +408,206 @@
       "mean_token_accuracy": 0.9370592629909515,
       "num_tokens": 16532116.0,
       "step": 1000
+    },
+    {
+      "entropy": 0.25085023198276757,
+      "epoch": 0.48423290421636944,
+      "grad_norm": 0.28125,
+      "learning_rate": 9.886701615567638e-05,
+      "loss": 0.2465,
+      "mean_token_accuracy": 0.9340272305905819,
+      "num_tokens": 16953093.0,
+      "step": 1025
+    },
+    {
+      "entropy": 0.2260630092769861,
+      "epoch": 0.4960434628557931,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 9.871695705615726e-05,
+      "loss": 0.2226,
+      "mean_token_accuracy": 0.9398330296576023,
+      "num_tokens": 17370548.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.22553566984832288,
+      "epoch": 0.5078540214952167,
+      "grad_norm": 0.2578125,
+      "learning_rate": 9.85576972621137e-05,
+      "loss": 0.2204,
+      "mean_token_accuracy": 0.9398049999773502,
+      "num_tokens": 17776168.0,
+      "step": 1075
+    },
+    {
+      "entropy": 0.22235366519540548,
+      "epoch": 0.5196645801346403,
+      "grad_norm": 0.255859375,
+      "learning_rate": 9.838926685138316e-05,
+      "loss": 0.2185,
+      "mean_token_accuracy": 0.9404512317478657,
+      "num_tokens": 18184751.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.22692312018945812,
+      "epoch": 0.531475138774064,
+      "grad_norm": 0.27734375,
+      "learning_rate": 9.821169763376763e-05,
+      "loss": 0.2211,
+      "mean_token_accuracy": 0.939469782114029,
+      "num_tokens": 18593080.0,
+      "step": 1125
+    },
+    {
+      "entropy": 0.22736175518482923,
+      "epoch": 0.5432856974134876,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 9.802502314502607e-05,
+      "loss": 0.224,
+      "mean_token_accuracy": 0.9391257779300213,
+      "num_tokens": 19006337.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.22326932862401008,
+      "epoch": 0.5550962560529114,
+      "grad_norm": 0.259765625,
+      "learning_rate": 9.782927864054075e-05,
+      "loss": 0.2207,
+      "mean_token_accuracy": 0.9402251268923283,
+      "num_tokens": 19408218.0,
+      "step": 1175
+    },
+    {
+      "entropy": 0.21780600540339948,
+      "epoch": 0.566906814692335,
+      "grad_norm": 0.294921875,
+      "learning_rate": 9.762450108865908e-05,
+      "loss": 0.2149,
+      "mean_token_accuracy": 0.9419379141926766,
+      "num_tokens": 19824621.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.21694308878853918,
+      "epoch": 0.5787173733317585,
+      "grad_norm": 0.2734375,
+      "learning_rate": 9.741072916371157e-05,
+      "loss": 0.2118,
+      "mean_token_accuracy": 0.9426406294107437,
+      "num_tokens": 20253370.0,
+      "step": 1225
+    },
+    {
+      "entropy": 0.20722413221374153,
+      "epoch": 0.5905279319711823,
+      "grad_norm": 0.220703125,
+      "learning_rate": 9.718800323870792e-05,
+      "loss": 0.2032,
+      "mean_token_accuracy": 0.9452938529849052,
+      "num_tokens": 20667551.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.21645578092895448,
+      "epoch": 0.6023384906106058,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 9.695636537771212e-05,
+      "loss": 0.2123,
+      "mean_token_accuracy": 0.9423565396666527,
+      "num_tokens": 21073835.0,
+      "step": 1275
+    },
+    {
+      "entropy": 0.20943242628127337,
+      "epoch": 0.6141490492500296,
+      "grad_norm": 0.251953125,
+      "learning_rate": 9.671585932789821e-05,
+      "loss": 0.2062,
+      "mean_token_accuracy": 0.9441554906964302,
+      "num_tokens": 21484157.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.20016088901087642,
+      "epoch": 0.6259596078894532,
+      "grad_norm": 0.314453125,
+      "learning_rate": 9.64665305112882e-05,
+      "loss": 0.1956,
+      "mean_token_accuracy": 0.9467314165830613,
+      "num_tokens": 21892824.0,
+      "step": 1325
+    },
+    {
+      "entropy": 0.2107498816680163,
+      "epoch": 0.6377701665288769,
+      "grad_norm": 0.287109375,
+      "learning_rate": 9.620842601617366e-05,
+      "loss": 0.2073,
+      "mean_token_accuracy": 0.9435116010904312,
+      "num_tokens": 22305526.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.1972426986414939,
+      "epoch": 0.6495807251683005,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 9.594159458822257e-05,
+      "loss": 0.1938,
+      "mean_token_accuracy": 0.9460577602684498,
+      "num_tokens": 22716778.0,
+      "step": 1375
+    },
+    {
+      "entropy": 0.19388799883425237,
+      "epoch": 0.661391283807724,
+      "grad_norm": 0.1953125,
+      "learning_rate": 9.56660866212733e-05,
+      "loss": 0.1893,
+      "mean_token_accuracy": 0.9480688716471195,
+      "num_tokens": 23139666.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.19959449878893792,
+      "epoch": 0.6732018424471478,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 9.538195414781707e-05,
+      "loss": 0.1964,
+      "mean_token_accuracy": 0.9466811017692089,
+      "num_tokens": 23541786.0,
+      "step": 1425
+    },
+    {
+      "entropy": 0.2100939876586199,
+      "epoch": 0.6850124010865714,
+      "grad_norm": 0.22265625,
+      "learning_rate": 9.50892508291713e-05,
+      "loss": 0.2064,
+      "mean_token_accuracy": 0.9439319328963757,
+      "num_tokens": 23951416.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.19447497643530368,
+      "epoch": 0.6968229597259951,
+      "grad_norm": 0.2265625,
+      "learning_rate": 9.478803194534486e-05,
+      "loss": 0.1914,
+      "mean_token_accuracy": 0.9480419178307057,
+      "num_tokens": 24374545.0,
+      "step": 1475
+    },
+    {
+      "entropy": 0.1884359281975776,
+      "epoch": 0.7086335183654187,
+      "grad_norm": 0.22265625,
+      "learning_rate": 9.447835438459811e-05,
+      "loss": 0.185,
+      "mean_token_accuracy": 0.9487812982499599,
+      "num_tokens": 24793698.0,
+      "step": 1500
     }
   ],
   "logging_steps": 25,
@@ -427,7 +627,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0567860712982623e+18,
+  "total_flos": 1.587361750240276e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null