Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40de222a643a29f7d83ca57461447e94369db28dfe02ce1ea8dc42c4841ff5b0
+oid sha256:aa4c5a2f220199565c612d1b585e05a7b92fff44644cb0d5fe3e2f43506e0e66
 size 517931840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17390b38b97f3c88d7498ab8a8662e59b4ff06eff339b6bdbd74ab3397b0fd3a
+oid sha256:6389d8c90e4661170f94cbc7fb36a5d3b74c5a0f6b13c2a19b9518515670df99
 size 1035661434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060f0503489879d8dfb53b047f548ca4611036feac0d8375d9686aebe8f546f0
+oid sha256:bf18e0901d5cf90634d477e2ea56f1da923039f227c0abc08997f7c74e97f4e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a106eb944d9a54ad09b68ad887887e7f10d1565ba0db56d5847127b57e2c1043
+oid sha256:00e07de65a0221f25bbdd3fefea6366e38c04a216122618dd72af76e955ce943
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1976943891861169,
+  "epoch": 0.21966043242901878,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1610,11 +1610,189 @@
       "eval_steps_per_second": 18.972,
       "num_input_tokens_seen": 9437184000,
       "step": 9000
+    },
+    {
+      "epoch": 0.198792691348262,
+      "grad_norm": 0.17666102945804596,
+      "learning_rate": 0.001,
+      "loss": 3.0728,
+      "num_input_tokens_seen": 9489612800,
+      "step": 9050
+    },
+    {
+      "epoch": 0.1998909935104071,
+      "grad_norm": 0.202484592795372,
+      "learning_rate": 0.001,
+      "loss": 2.9818,
+      "num_input_tokens_seen": 9542041600,
+      "step": 9100
+    },
+    {
+      "epoch": 0.2009892956725522,
+      "grad_norm": 0.15095236897468567,
+      "learning_rate": 0.001,
+      "loss": 2.9423,
+      "num_input_tokens_seen": 9594470400,
+      "step": 9150
+    },
+    {
+      "epoch": 0.2020875978346973,
+      "grad_norm": 0.13089850544929504,
+      "learning_rate": 0.001,
+      "loss": 2.9227,
+      "num_input_tokens_seen": 9646899200,
+      "step": 9200
+    },
+    {
+      "epoch": 0.2031858999968424,
+      "grad_norm": 0.14022304117679596,
+      "learning_rate": 0.001,
+      "loss": 2.8988,
+      "num_input_tokens_seen": 9699328000,
+      "step": 9250
+    },
+    {
+      "epoch": 0.2042842021589875,
+      "grad_norm": 0.13116785883903503,
+      "learning_rate": 0.001,
+      "loss": 2.8716,
+      "num_input_tokens_seen": 9751756800,
+      "step": 9300
+    },
+    {
+      "epoch": 0.20538250432113256,
+      "grad_norm": 0.1395471841096878,
+      "learning_rate": 0.001,
+      "loss": 2.8727,
+      "num_input_tokens_seen": 9804185600,
+      "step": 9350
+    },
+    {
+      "epoch": 0.20648080648327766,
+      "grad_norm": 0.1271878033876419,
+      "learning_rate": 0.001,
+      "loss": 2.864,
+      "num_input_tokens_seen": 9856614400,
+      "step": 9400
+    },
+    {
+      "epoch": 0.20757910864542276,
+      "grad_norm": 0.14148685336112976,
+      "learning_rate": 0.001,
+      "loss": 2.8604,
+      "num_input_tokens_seen": 9909043200,
+      "step": 9450
+    },
+    {
+      "epoch": 0.20867741080756785,
+      "grad_norm": 0.1292584091424942,
+      "learning_rate": 0.001,
+      "loss": 2.8547,
+      "num_input_tokens_seen": 9961472000,
+      "step": 9500
+    },
+    {
+      "epoch": 0.20867741080756785,
+      "eval_loss": 2.756131649017334,
+      "eval_runtime": 65.0495,
+      "eval_samples_per_second": 76.865,
+      "eval_steps_per_second": 19.216,
+      "num_input_tokens_seen": 9961472000,
+      "step": 9500
+    },
+    {
+      "epoch": 0.20977571296971295,
+      "grad_norm": 0.10929372161626816,
+      "learning_rate": 0.001,
+      "loss": 2.8467,
+      "num_input_tokens_seen": 10013900800,
+      "step": 9550
+    },
+    {
+      "epoch": 0.21087401513185805,
+      "grad_norm": 0.1180899515748024,
+      "learning_rate": 0.001,
+      "loss": 2.8501,
+      "num_input_tokens_seen": 10066329600,
+      "step": 9600
+    },
+    {
+      "epoch": 0.21197231729400312,
+      "grad_norm": 0.12041448056697845,
+      "learning_rate": 0.001,
+      "loss": 2.8438,
+      "num_input_tokens_seen": 10118758400,
+      "step": 9650
+    },
+    {
+      "epoch": 0.21307061945614822,
+      "grad_norm": 0.13195224106311798,
+      "learning_rate": 0.001,
+      "loss": 2.8341,
+      "num_input_tokens_seen": 10171187200,
+      "step": 9700
+    },
+    {
+      "epoch": 0.21416892161829332,
+      "grad_norm": 0.11887054890394211,
+      "learning_rate": 0.001,
+      "loss": 2.8349,
+      "num_input_tokens_seen": 10223616000,
+      "step": 9750
+    },
+    {
+      "epoch": 0.21526722378043842,
+      "grad_norm": 0.1044996827840805,
+      "learning_rate": 0.001,
+      "loss": 2.8428,
+      "num_input_tokens_seen": 10276044800,
+      "step": 9800
+    },
+    {
+      "epoch": 0.21636552594258351,
+      "grad_norm": 0.11951665580272675,
+      "learning_rate": 0.001,
+      "loss": 2.8323,
+      "num_input_tokens_seen": 10328473600,
+      "step": 9850
+    },
+    {
+      "epoch": 0.2174638281047286,
+      "grad_norm": 0.11673793941736221,
+      "learning_rate": 0.001,
+      "loss": 2.8271,
+      "num_input_tokens_seen": 10380902400,
+      "step": 9900
+    },
+    {
+      "epoch": 0.21856213026687368,
+      "grad_norm": 0.1178969219326973,
+      "learning_rate": 0.001,
+      "loss": 2.8328,
+      "num_input_tokens_seen": 10433331200,
+      "step": 9950
+    },
+    {
+      "epoch": 0.21966043242901878,
+      "grad_norm": 0.11995361745357513,
+      "learning_rate": 0.001,
+      "loss": 2.8182,
+      "num_input_tokens_seen": 10485760000,
+      "step": 10000
+    },
+    {
+      "epoch": 0.21966043242901878,
+      "eval_loss": 2.732673168182373,
+      "eval_runtime": 66.3377,
+      "eval_samples_per_second": 75.372,
+      "eval_steps_per_second": 18.843,
+      "num_input_tokens_seen": 10485760000,
+      "step": 10000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 9437184000,
+  "num_input_tokens_seen": 10485760000,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -1629,7 +1807,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.374545443684352e+18,
+  "total_flos": 5.97171715964928e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null