Training in progress, step 70000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:255db0ba45691d582a9ee109acc81eb21c645c6dd171a1bf2c3e231a0982d734
+oid sha256:b2cd2d83e8bcf2e24c3dfb835a421fc560d30e2495b3907943e618272cae7419
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78af01c29bc4dc4815cd8cb2a0e12aac4f0221e2ad669f18caa4315a15ef83d7
+oid sha256:976f02141679563933b488383c3b486345d46612fec4531d1a034013ee84ec05
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1397d04798a1fd86f4b074ba5cc769a269eab9bb0994d2bcfee86faa58f609a6
+oid sha256:f91f0395ad8bb44fd81f1444330dede040f6b66dbc15e61e2a7fe4c1ef60aa2a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16992573f9fe212ca32ce6bacf3d51d66103db65f351073047f24fab4f0f55af
+oid sha256:8c3a675e6db9104dd282c679a41cb4bdc17a98118d756c948d809458e24a6b37
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3291317361699083,
+  "epoch": 0.333901761331791,
   "eval_steps": 500,
-  "global_step": 69000,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12290,11 +12290,189 @@
       "eval_steps_per_second": 23.618,
       "num_input_tokens_seen": 18087931456,
       "step": 69000
+    },
+    {
+      "epoch": 0.3293702374280024,
+      "grad_norm": 0.14565595984458923,
+      "learning_rate": 1.1318413143740436e-05,
+      "loss": 2.5358,
+      "num_input_tokens_seen": 18101038656,
+      "step": 69050
+    },
+    {
+      "epoch": 0.3296087386860966,
+      "grad_norm": 0.15810008347034454,
+      "learning_rate": 1.0162300788382261e-05,
+      "loss": 2.5288,
+      "num_input_tokens_seen": 18114145856,
+      "step": 69100
+    },
+    {
+      "epoch": 0.3298472399441907,
+      "grad_norm": 0.14960281550884247,
+      "learning_rate": 9.0678523819408e-06,
+      "loss": 2.5267,
+      "num_input_tokens_seen": 18127253056,
+      "step": 69150
+    },
+    {
+      "epoch": 0.33008574120228484,
+      "grad_norm": 0.14473624527454376,
+      "learning_rate": 8.035205700685167e-06,
+      "loss": 2.5133,
+      "num_input_tokens_seen": 18140360256,
+      "step": 69200
+    },
+    {
+      "epoch": 0.330324242460379,
+      "grad_norm": 0.1450708657503128,
+      "learning_rate": 7.064490740882057e-06,
+      "loss": 2.5302,
+      "num_input_tokens_seen": 18153467456,
+      "step": 69250
+    },
+    {
+      "epoch": 0.3305627437184731,
+      "grad_norm": 0.14883211255073547,
+      "learning_rate": 6.15582970243117e-06,
+      "loss": 2.5307,
+      "num_input_tokens_seen": 18166574656,
+      "step": 69300
+    },
+    {
+      "epoch": 0.33080124497656727,
+      "grad_norm": 0.15696081519126892,
+      "learning_rate": 5.309336973481682e-06,
+      "loss": 2.5341,
+      "num_input_tokens_seen": 18179681856,
+      "step": 69350
+    },
+    {
+      "epoch": 0.33103974623466137,
+      "grad_norm": 0.1564367264509201,
+      "learning_rate": 4.52511911603265e-06,
+      "loss": 2.5299,
+      "num_input_tokens_seen": 18192789056,
+      "step": 69400
+    },
+    {
+      "epoch": 0.33127824749275553,
+      "grad_norm": 0.15558916330337524,
+      "learning_rate": 3.803274852517968e-06,
+      "loss": 2.5197,
+      "num_input_tokens_seen": 18205896256,
+      "step": 69450
+    },
+    {
+      "epoch": 0.3315167487508497,
+      "grad_norm": 0.1532556265592575,
+      "learning_rate": 3.143895053378698e-06,
+      "loss": 2.5176,
+      "num_input_tokens_seen": 18219003456,
+      "step": 69500
+    },
+    {
+      "epoch": 0.3315167487508497,
+      "eval_loss": 2.412046194076538,
+      "eval_runtime": 53.2476,
+      "eval_samples_per_second": 93.901,
+      "eval_steps_per_second": 23.475,
+      "num_input_tokens_seen": 18219003456,
+      "step": 69500
+    },
+    {
+      "epoch": 0.3317552500089438,
+      "grad_norm": 0.1502823829650879,
+      "learning_rate": 2.547062725623828e-06,
+      "loss": 2.5207,
+      "num_input_tokens_seen": 18232110656,
+      "step": 69550
+    },
+    {
+      "epoch": 0.33199375126703795,
+      "grad_norm": 0.1560440957546234,
+      "learning_rate": 2.012853002380466e-06,
+      "loss": 2.5078,
+      "num_input_tokens_seen": 18245217856,
+      "step": 69600
+    },
+    {
+      "epoch": 0.33223225252513205,
+      "grad_norm": 0.15284490585327148,
+      "learning_rate": 1.541333133436018e-06,
+      "loss": 2.5404,
+      "num_input_tokens_seen": 18258325056,
+      "step": 69650
+    },
+    {
+      "epoch": 0.3324707537832262,
+      "grad_norm": 0.14594900608062744,
+      "learning_rate": 1.132562476771959e-06,
+      "loss": 2.5267,
+      "num_input_tokens_seen": 18271432256,
+      "step": 69700
+    },
+    {
+      "epoch": 0.3327092550413203,
+      "grad_norm": 0.15198394656181335,
+      "learning_rate": 7.865924910916978e-07,
+      "loss": 2.5232,
+      "num_input_tokens_seen": 18284539456,
+      "step": 69750
+    },
+    {
+      "epoch": 0.3329477562994145,
+      "grad_norm": 0.15011271834373474,
+      "learning_rate": 5.034667293427053e-07,
+      "loss": 2.5308,
+      "num_input_tokens_seen": 18297646656,
+      "step": 69800
+    },
+    {
+      "epoch": 0.33318625755750864,
+      "grad_norm": 0.147654727101326,
+      "learning_rate": 2.8322083323334415e-07,
+      "loss": 2.5281,
+      "num_input_tokens_seen": 18310753856,
+      "step": 69850
+    },
+    {
+      "epoch": 0.33342475881560274,
+      "grad_norm": 0.15056386590003967,
+      "learning_rate": 1.2588252874673466e-07,
+      "loss": 2.5112,
+      "num_input_tokens_seen": 18323861056,
+      "step": 69900
+    },
+    {
+      "epoch": 0.3336632600736969,
+      "grad_norm": 0.14858213067054749,
+      "learning_rate": 3.147162264971471e-08,
+      "loss": 2.5226,
+      "num_input_tokens_seen": 18336968256,
+      "step": 69950
+    },
+    {
+      "epoch": 0.333901761331791,
+      "grad_norm": 0.1534891128540039,
+      "learning_rate": 0.0,
+      "loss": 2.5303,
+      "num_input_tokens_seen": 18350075456,
+      "step": 70000
+    },
+    {
+      "epoch": 0.333901761331791,
+      "eval_loss": 2.411842107772827,
+      "eval_runtime": 53.9812,
+      "eval_samples_per_second": 92.625,
+      "eval_steps_per_second": 23.156,
+      "num_input_tokens_seen": 18350075456,
+      "step": 70000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 18087931456,
+  "num_input_tokens_seen": 18350075456,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -12304,12 +12482,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.838698202691011e+18,
+  "total_flos": 4.908824281216451e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null