Training in progress, step 149000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49af2707fb3112eeed61ee13c290911c69079884a01f5f58dac07e1cd882f8b1
+oid sha256:0b87dded127d40fd82c03235b1698dfe33a8b5f87187ba074bf40022236624c6
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0dfd486869999f269b0f0074251b163c07b9592c1d23c6f430a2587dd3aab49
+oid sha256:23c47d38cecaa63e531df29e38e9afb0727c11e9a4b57b059ee2acbb0fb1f4d3
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e431ae70535003e66588edeeb1d633c5a84304655770f2de2a82e8a43acc3d
+oid sha256:4b3f339c8acfe7277fe2df77c27fc1a5816faed78935e9068ab888b7bb106bcc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2faea7290e2b3162494872c13e093462ac71f54739ae3866b541ee62eaf6f6fd
+oid sha256:c40e8b457d57718c67b26e249dafca477bb77feb974e04c20b75eee25d0b14aa
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.251028114495333,
+  "epoch": 3.272994172816591,
   "eval_steps": 500,
-  "global_step": 148000,
+  "global_step": 149000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -26352,11 +26352,189 @@
       "eval_steps_per_second": 15.617,
       "num_input_tokens_seen": 81776845856,
       "step": 148000
+    },
+    {
+      "epoch": 3.252126417411396,
+      "grad_norm": 0.09104160964488983,
+      "learning_rate": 0.0001,
+      "loss": 2.3493,
+      "num_input_tokens_seen": 81829274656,
+      "step": 148050
+    },
+    {
+      "epoch": 3.253224720327459,
+      "grad_norm": 0.09389001131057739,
+      "learning_rate": 0.0001,
+      "loss": 2.3517,
+      "num_input_tokens_seen": 81881698752,
+      "step": 148100
+    },
+    {
+      "epoch": 3.254323023243522,
+      "grad_norm": 0.09085691720247269,
+      "learning_rate": 0.0001,
+      "loss": 2.3449,
+      "num_input_tokens_seen": 81934124352,
+      "step": 148150
+    },
+    {
+      "epoch": 3.255421326159585,
+      "grad_norm": 0.09462492913007736,
+      "learning_rate": 0.0001,
+      "loss": 2.3535,
+      "num_input_tokens_seen": 81986553152,
+      "step": 148200
+    },
+    {
+      "epoch": 3.2565196290756475,
+      "grad_norm": 0.09079829603433609,
+      "learning_rate": 0.0001,
+      "loss": 2.3477,
+      "num_input_tokens_seen": 82038981952,
+      "step": 148250
+    },
+    {
+      "epoch": 3.2576179319917107,
+      "grad_norm": 0.09165850281715393,
+      "learning_rate": 0.0001,
+      "loss": 2.3548,
+      "num_input_tokens_seen": 82091407040,
+      "step": 148300
+    },
+    {
+      "epoch": 3.2587162349077734,
+      "grad_norm": 0.09388460963964462,
+      "learning_rate": 0.0001,
+      "loss": 2.3477,
+      "num_input_tokens_seen": 82143834912,
+      "step": 148350
+    },
+    {
+      "epoch": 3.2598145378238366,
+      "grad_norm": 0.09309230744838715,
+      "learning_rate": 0.0001,
+      "loss": 2.3506,
+      "num_input_tokens_seen": 82196262432,
+      "step": 148400
+    },
+    {
+      "epoch": 3.2609128407398993,
+      "grad_norm": 0.09229093790054321,
+      "learning_rate": 0.0001,
+      "loss": 2.3451,
+      "num_input_tokens_seen": 82248691232,
+      "step": 148450
+    },
+    {
+      "epoch": 3.262011143655962,
+      "grad_norm": 0.09784185886383057,
+      "learning_rate": 0.0001,
+      "loss": 2.3447,
+      "num_input_tokens_seen": 82301120032,
+      "step": 148500
+    },
+    {
+      "epoch": 3.262011143655962,
+      "eval_loss": 2.2628486156463623,
+      "eval_runtime": 80.5596,
+      "eval_samples_per_second": 62.066,
+      "eval_steps_per_second": 15.516,
+      "num_input_tokens_seen": 82301120032,
+      "step": 148500
+    },
+    {
+      "epoch": 3.263109446572025,
+      "grad_norm": 0.09117227792739868,
+      "learning_rate": 0.0001,
+      "loss": 2.3541,
+      "num_input_tokens_seen": 82353545696,
+      "step": 148550
+    },
+    {
+      "epoch": 3.264207749488088,
+      "grad_norm": 0.09306716918945312,
+      "learning_rate": 0.0001,
+      "loss": 2.3522,
+      "num_input_tokens_seen": 82405974496,
+      "step": 148600
+    },
+    {
+      "epoch": 3.2653060524041506,
+      "grad_norm": 0.0911402553319931,
+      "learning_rate": 0.0001,
+      "loss": 2.3479,
+      "num_input_tokens_seen": 82458403296,
+      "step": 148650
+    },
+    {
+      "epoch": 3.266404355320214,
+      "grad_norm": 0.09247133135795593,
+      "learning_rate": 0.0001,
+      "loss": 2.3459,
+      "num_input_tokens_seen": 82510832096,
+      "step": 148700
+    },
+    {
+      "epoch": 3.2675026582362765,
+      "grad_norm": 0.08942971378564835,
+      "learning_rate": 0.0001,
+      "loss": 2.3442,
+      "num_input_tokens_seen": 82563260896,
+      "step": 148750
+    },
+    {
+      "epoch": 3.2686009611523392,
+      "grad_norm": 0.09245148301124573,
+      "learning_rate": 0.0001,
+      "loss": 2.3455,
+      "num_input_tokens_seen": 82615689600,
+      "step": 148800
+    },
+    {
+      "epoch": 3.2696992640684024,
+      "grad_norm": 0.09015721827745438,
+      "learning_rate": 0.0001,
+      "loss": 2.3502,
+      "num_input_tokens_seen": 82668116128,
+      "step": 148850
+    },
+    {
+      "epoch": 3.270797566984465,
+      "grad_norm": 0.1070784255862236,
+      "learning_rate": 0.0001,
+      "loss": 2.3561,
+      "num_input_tokens_seen": 82720544928,
+      "step": 148900
+    },
+    {
+      "epoch": 3.2718958699005283,
+      "grad_norm": 0.09262741357088089,
+      "learning_rate": 0.0001,
+      "loss": 2.343,
+      "num_input_tokens_seen": 82772973728,
+      "step": 148950
+    },
+    {
+      "epoch": 3.272994172816591,
+      "grad_norm": 0.0885642021894455,
+      "learning_rate": 0.0001,
+      "loss": 2.3477,
+      "num_input_tokens_seen": 82825402528,
+      "step": 149000
+    },
+    {
+      "epoch": 3.272994172816591,
+      "eval_loss": 2.262723684310913,
+      "eval_runtime": 80.9161,
+      "eval_samples_per_second": 61.792,
+      "eval_steps_per_second": 15.448,
+      "num_input_tokens_seen": 82825402528,
+      "step": 149000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 81776845856,
+  "num_input_tokens_seen": 82825402528,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -26371,7 +26549,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4473010106843587e+20,
+  "total_flos": 1.465858551211389e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null