Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278b8b2d84624a5cae264faca78faa492c08b956ba242e903164c6891b75a79a
+oid sha256:5cf815e6e63a17cdb9abef6d6a034aa11cda747870482f601096bc7eaaced8b8
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa31674146f290bd37e50903cc3d4904939c0d1f87ac265d2179a8b359f0c7e
+oid sha256:ef8663185aa879cdc6c96017209b8ea400dc73cec0abf37f93a6946d8b844fc7
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8673bcb3ee42f37006ee0b6987fffb72c83f6be35be42973cab2ef49242d2b2b
+oid sha256:0a7131d69ba7156fcfd8e4dfc557d7e121df2a1c1d83a47239788bb8dbd92b17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c3d80aaacee80212417a329afbc88c74b35bad8004900a2301b44b629b4ab7
+oid sha256:6662ae68d38995d5846f13e724946a2acb1395046b7d08977dde3dab733945c0
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09063047807577185,
+  "epoch": 0.09540050323765457,
   "eval_steps": 500,
-  "global_step": 19000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3390,11 +3390,189 @@
       "eval_steps_per_second": 24.604,
       "num_input_tokens_seen": 4980736000,
       "step": 19000
+    },
+    {
+      "epoch": 0.09086897933386599,
+      "grad_norm": 0.1770928055047989,
+      "learning_rate": 0.001,
+      "loss": 2.7171,
+      "num_input_tokens_seen": 4993843200,
+      "step": 19050
+    },
+    {
+      "epoch": 0.09110748059196012,
+      "grad_norm": 0.18122689425945282,
+      "learning_rate": 0.001,
+      "loss": 2.7064,
+      "num_input_tokens_seen": 5006950400,
+      "step": 19100
+    },
+    {
+      "epoch": 0.09134598185005426,
+      "grad_norm": 0.19320747256278992,
+      "learning_rate": 0.001,
+      "loss": 2.7105,
+      "num_input_tokens_seen": 5020057600,
+      "step": 19150
+    },
+    {
+      "epoch": 0.0915844831081484,
+      "grad_norm": 0.19556616246700287,
+      "learning_rate": 0.001,
+      "loss": 2.7018,
+      "num_input_tokens_seen": 5033164800,
+      "step": 19200
+    },
+    {
+      "epoch": 0.09182298436624253,
+      "grad_norm": 0.18251653015613556,
+      "learning_rate": 0.001,
+      "loss": 2.7067,
+      "num_input_tokens_seen": 5046272000,
+      "step": 19250
+    },
+    {
+      "epoch": 0.09206148562433666,
+      "grad_norm": 0.17226757109165192,
+      "learning_rate": 0.001,
+      "loss": 2.6803,
+      "num_input_tokens_seen": 5059379200,
+      "step": 19300
+    },
+    {
+      "epoch": 0.09229998688243081,
+      "grad_norm": 0.18007858097553253,
+      "learning_rate": 0.001,
+      "loss": 2.6998,
+      "num_input_tokens_seen": 5072486400,
+      "step": 19350
+    },
+    {
+      "epoch": 0.09253848814052494,
+      "grad_norm": 0.1664605736732483,
+      "learning_rate": 0.001,
+      "loss": 2.6985,
+      "num_input_tokens_seen": 5085593600,
+      "step": 19400
+    },
+    {
+      "epoch": 0.09277698939861907,
+      "grad_norm": 0.17898677289485931,
+      "learning_rate": 0.001,
+      "loss": 2.7034,
+      "num_input_tokens_seen": 5098700800,
+      "step": 19450
+    },
+    {
+      "epoch": 0.09301549065671322,
+      "grad_norm": 0.16403160989284515,
+      "learning_rate": 0.001,
+      "loss": 2.7012,
+      "num_input_tokens_seen": 5111808000,
+      "step": 19500
+    },
+    {
+      "epoch": 0.09301549065671322,
+      "eval_loss": 2.594251871109009,
+      "eval_runtime": 50.1924,
+      "eval_samples_per_second": 99.617,
+      "eval_steps_per_second": 24.904,
+      "num_input_tokens_seen": 5111808000,
+      "step": 19500
+    },
+    {
+      "epoch": 0.09325399191480735,
+      "grad_norm": 0.17973001301288605,
+      "learning_rate": 0.001,
+      "loss": 2.7039,
+      "num_input_tokens_seen": 5124915200,
+      "step": 19550
+    },
+    {
+      "epoch": 0.09349249317290148,
+      "grad_norm": 0.1667868047952652,
+      "learning_rate": 0.001,
+      "loss": 2.7038,
+      "num_input_tokens_seen": 5138022400,
+      "step": 19600
+    },
+    {
+      "epoch": 0.09373099443099563,
+      "grad_norm": 0.18338319659233093,
+      "learning_rate": 0.001,
+      "loss": 2.7138,
+      "num_input_tokens_seen": 5151129600,
+      "step": 19650
+    },
+    {
+      "epoch": 0.09396949568908976,
+      "grad_norm": 0.17962965369224548,
+      "learning_rate": 0.001,
+      "loss": 2.6994,
+      "num_input_tokens_seen": 5164236800,
+      "step": 19700
+    },
+    {
+      "epoch": 0.0942079969471839,
+      "grad_norm": 0.17233812808990479,
+      "learning_rate": 0.001,
+      "loss": 2.7073,
+      "num_input_tokens_seen": 5177344000,
+      "step": 19750
+    },
+    {
+      "epoch": 0.09444649820527803,
+      "grad_norm": 0.16720129549503326,
+      "learning_rate": 0.001,
+      "loss": 2.7146,
+      "num_input_tokens_seen": 5190451200,
+      "step": 19800
+    },
+    {
+      "epoch": 0.09468499946337217,
+      "grad_norm": 0.1732376664876938,
+      "learning_rate": 0.001,
+      "loss": 2.7126,
+      "num_input_tokens_seen": 5203558400,
+      "step": 19850
+    },
+    {
+      "epoch": 0.09492350072146631,
+      "grad_norm": 0.17245380580425262,
+      "learning_rate": 0.001,
+      "loss": 2.7054,
+      "num_input_tokens_seen": 5216665600,
+      "step": 19900
+    },
+    {
+      "epoch": 0.09516200197956044,
+      "grad_norm": 0.17415107786655426,
+      "learning_rate": 0.001,
+      "loss": 2.7027,
+      "num_input_tokens_seen": 5229772800,
+      "step": 19950
+    },
+    {
+      "epoch": 0.09540050323765457,
+      "grad_norm": 0.1747124344110489,
+      "learning_rate": 0.001,
+      "loss": 2.6975,
+      "num_input_tokens_seen": 5242880000,
+      "step": 20000
+    },
+    {
+      "epoch": 0.09540050323765457,
+      "eval_loss": 2.5900332927703857,
+      "eval_runtime": 50.5898,
+      "eval_samples_per_second": 98.834,
+      "eval_steps_per_second": 24.709,
+      "num_input_tokens_seen": 5242880000,
+      "step": 20000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 4980736000,
+  "num_input_tokens_seen": 5242880000,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -3409,7 +3587,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.33239549198336e+18,
+  "total_flos": 1.4025215705088e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null