Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bc77814a9f0609f35da88bd498f09fe67c0ec6e846f95d060a6c4b10a82b17
+oid sha256:d922a368949a5441e9d489b35470030cb4c615391e10cc7551d311fbbe8f4950
 size 517931840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124d39c4cbb90f633e078a9fc2ec3d64bd1a263157af6537f15cbfbe1041beb8
+oid sha256:289467f36f723eb875d041ff89803400a785f51c542f023d361eafe581c907c6
 size 1035661434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f709c9b1d30b7448b89cdbd3384985d3e5e1529a919cf635b9e29a00476e9e36
+oid sha256:6cbeff8537e701321b2075efc2eebe11299a3bd7caeea31b1272c71b85f04f18
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc38559b8af23697273496301060a7de66bceefb1f96fb5cbe737d317e8e471
+oid sha256:4c0af51cb41f8d18ef1a20793cfc25e481d976840ad64e5c8a2edb4c4b13f606
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15376230270031316,
+  "epoch": 0.17572834594321504,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1254,11 +1254,189 @@
       "eval_steps_per_second": 19.133,
       "num_input_tokens_seen": 7340032000,
       "step": 7000
+    },
+    {
+      "epoch": 0.15486060486245826,
+      "grad_norm": 0.11222469806671143,
+      "learning_rate": 0.001,
+      "loss": 2.8997,
+      "num_input_tokens_seen": 7392460800,
+      "step": 7050
+    },
+    {
+      "epoch": 0.15595890702460335,
+      "grad_norm": 0.11488104611635208,
+      "learning_rate": 0.001,
+      "loss": 2.8965,
+      "num_input_tokens_seen": 7444889600,
+      "step": 7100
+    },
+    {
+      "epoch": 0.15705720918674843,
+      "grad_norm": 0.1285555213689804,
+      "learning_rate": 0.001,
+      "loss": 2.8909,
+      "num_input_tokens_seen": 7497318400,
+      "step": 7150
+    },
+    {
+      "epoch": 0.15815551134889352,
+      "grad_norm": 0.12659265100955963,
+      "learning_rate": 0.001,
+      "loss": 2.8833,
+      "num_input_tokens_seen": 7549747200,
+      "step": 7200
+    },
+    {
+      "epoch": 0.15925381351103862,
+      "grad_norm": 0.10823842883110046,
+      "learning_rate": 0.001,
+      "loss": 2.9031,
+      "num_input_tokens_seen": 7602176000,
+      "step": 7250
+    },
+    {
+      "epoch": 0.16035211567318372,
+      "grad_norm": 0.12597811222076416,
+      "learning_rate": 0.001,
+      "loss": 2.8831,
+      "num_input_tokens_seen": 7654604800,
+      "step": 7300
+    },
+    {
+      "epoch": 0.16145041783532882,
+      "grad_norm": 0.1285410374403,
+      "learning_rate": 0.001,
+      "loss": 2.8931,
+      "num_input_tokens_seen": 7707033600,
+      "step": 7350
+    },
+    {
+      "epoch": 0.16254871999747392,
+      "grad_norm": 0.11170299351215363,
+      "learning_rate": 0.001,
+      "loss": 2.8861,
+      "num_input_tokens_seen": 7759462400,
+      "step": 7400
+    },
+    {
+      "epoch": 0.163647022159619,
+      "grad_norm": 0.11146055907011032,
+      "learning_rate": 0.001,
+      "loss": 2.8756,
+      "num_input_tokens_seen": 7811891200,
+      "step": 7450
+    },
+    {
+      "epoch": 0.1647453243217641,
+      "grad_norm": 0.10750412940979004,
+      "learning_rate": 0.001,
+      "loss": 2.8808,
+      "num_input_tokens_seen": 7864320000,
+      "step": 7500
+    },
+    {
+      "epoch": 0.1647453243217641,
+      "eval_loss": 2.785506248474121,
+      "eval_runtime": 65.0661,
+      "eval_samples_per_second": 76.845,
+      "eval_steps_per_second": 19.211,
+      "num_input_tokens_seen": 7864320000,
+      "step": 7500
+    },
+    {
+      "epoch": 0.16584362648390918,
+      "grad_norm": 0.11221355944871902,
+      "learning_rate": 0.001,
+      "loss": 2.8834,
+      "num_input_tokens_seen": 7916748800,
+      "step": 7550
+    },
+    {
+      "epoch": 0.16694192864605428,
+      "grad_norm": 0.1089220717549324,
+      "learning_rate": 0.001,
+      "loss": 2.8796,
+      "num_input_tokens_seen": 7969177600,
+      "step": 7600
+    },
+    {
+      "epoch": 0.16804023080819938,
+      "grad_norm": 0.11125486344099045,
+      "learning_rate": 0.001,
+      "loss": 2.8836,
+      "num_input_tokens_seen": 8021606400,
+      "step": 7650
+    },
+    {
+      "epoch": 0.16913853297034448,
+      "grad_norm": 0.12804660201072693,
+      "learning_rate": 0.001,
+      "loss": 2.8754,
+      "num_input_tokens_seen": 8074035200,
+      "step": 7700
+    },
+    {
+      "epoch": 0.17023683513248955,
+      "grad_norm": 0.11395713686943054,
+      "learning_rate": 0.001,
+      "loss": 2.8736,
+      "num_input_tokens_seen": 8126464000,
+      "step": 7750
+    },
+    {
+      "epoch": 0.17133513729463465,
+      "grad_norm": 0.1095738559961319,
+      "learning_rate": 0.001,
+      "loss": 2.8743,
+      "num_input_tokens_seen": 8178892800,
+      "step": 7800
+    },
+    {
+      "epoch": 0.17243343945677975,
+      "grad_norm": 0.10545111447572708,
+      "learning_rate": 0.001,
+      "loss": 2.8718,
+      "num_input_tokens_seen": 8231321600,
+      "step": 7850
+    },
+    {
+      "epoch": 0.17353174161892485,
+      "grad_norm": 0.13135021924972534,
+      "learning_rate": 0.001,
+      "loss": 2.8648,
+      "num_input_tokens_seen": 8283750400,
+      "step": 7900
+    },
+    {
+      "epoch": 0.17463004378106994,
+      "grad_norm": 0.12348899990320206,
+      "learning_rate": 0.001,
+      "loss": 2.8628,
+      "num_input_tokens_seen": 8336179200,
+      "step": 7950
+    },
+    {
+      "epoch": 0.17572834594321504,
+      "grad_norm": 0.10604492574930191,
+      "learning_rate": 0.001,
+      "loss": 2.8676,
+      "num_input_tokens_seen": 8388608000,
+      "step": 8000
+    },
+    {
+      "epoch": 0.17572834594321504,
+      "eval_loss": 2.7698919773101807,
+      "eval_runtime": 65.5096,
+      "eval_samples_per_second": 76.325,
+      "eval_steps_per_second": 19.081,
+      "num_input_tokens_seen": 8388608000,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 7340032000,
+  "num_input_tokens_seen": 8388608000,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -1273,7 +1451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.180202011754496e+18,
+  "total_flos": 4.777373727719424e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null