Training in progress, step 69000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b26db7188c89cde52f93cc8f561f4529a8702aaa52ce9c883892b96769dd603
+oid sha256:255db0ba45691d582a9ee109acc81eb21c645c6dd171a1bf2c3e231a0982d734
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec885f087630fd98da5aea6a3b9af5bf67a1e0daf9ab5c57e09d7f1ac7385946
+oid sha256:78af01c29bc4dc4815cd8cb2a0e12aac4f0221e2ad669f18caa4315a15ef83d7
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3d1fb9e8324a04c98053fb02a6fde8d1a865fd7ced6a674f76811c1bbb259f
+oid sha256:1397d04798a1fd86f4b074ba5cc769a269eab9bb0994d2bcfee86faa58f609a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb0106671a29e67305a03ecdd422ffd62f40cc2f3e19327fe3581d2d1603d90
+oid sha256:16992573f9fe212ca32ce6bacf3d51d66103db65f351073047f24fab4f0f55af
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3243617110080256,
+  "epoch": 0.3291317361699083,
   "eval_steps": 500,
-  "global_step": 68000,
+  "global_step": 69000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12112,11 +12112,189 @@
       "eval_steps_per_second": 23.177,
       "num_input_tokens_seen": 17825787456,
       "step": 68000
+    },
+    {
+      "epoch": 0.3246002122661197,
+      "grad_norm": 0.15067367255687714,
+      "learning_rate": 4.7109889986402973e-05,
+      "loss": 2.5181,
+      "num_input_tokens_seen": 17838894656,
+      "step": 68050
+    },
+    {
+      "epoch": 0.32483871352421384,
+      "grad_norm": 0.1534261703491211,
+      "learning_rate": 4.476122667059207e-05,
+      "loss": 2.533,
+      "num_input_tokens_seen": 17852001856,
+      "step": 68100
+    },
+    {
+      "epoch": 0.325077214782308,
+      "grad_norm": 0.1585472822189331,
+      "learning_rate": 4.2469871766340095e-05,
+      "loss": 2.509,
+      "num_input_tokens_seen": 17865109056,
+      "step": 68150
+    },
+    {
+      "epoch": 0.3253157160404021,
+      "grad_norm": 0.15480853617191315,
+      "learning_rate": 4.0236113724274713e-05,
+      "loss": 2.524,
+      "num_input_tokens_seen": 17878216256,
+      "step": 68200
+    },
+    {
+      "epoch": 0.32555421729849626,
+      "grad_norm": 0.24341611564159393,
+      "learning_rate": 3.806023374435663e-05,
+      "loss": 2.5293,
+      "num_input_tokens_seen": 17891323456,
+      "step": 68250
+    },
+    {
+      "epoch": 0.32579271855659037,
+      "grad_norm": 0.15290473401546478,
+      "learning_rate": 3.594250574048058e-05,
+      "loss": 2.5149,
+      "num_input_tokens_seen": 17904430656,
+      "step": 68300
+    },
+    {
+      "epoch": 0.3260312198146845,
+      "grad_norm": 0.1606835126876831,
+      "learning_rate": 3.3883196305992905e-05,
+      "loss": 2.5327,
+      "num_input_tokens_seen": 17917537856,
+      "step": 68350
+    },
+    {
+      "epoch": 0.3262697210727787,
+      "grad_norm": 0.1537574976682663,
+      "learning_rate": 3.18825646801314e-05,
+      "loss": 2.5416,
+      "num_input_tokens_seen": 17930645056,
+      "step": 68400
+    },
+    {
+      "epoch": 0.3265082223308728,
+      "grad_norm": 0.16943201422691345,
+      "learning_rate": 2.994086271539048e-05,
+      "loss": 2.5233,
+      "num_input_tokens_seen": 17943752256,
+      "step": 68450
+    },
+    {
+      "epoch": 0.32674672358896695,
+      "grad_norm": 0.15832561254501343,
+      "learning_rate": 2.8058334845816213e-05,
+      "loss": 2.5439,
+      "num_input_tokens_seen": 17956859456,
+      "step": 68500
+    },
+    {
+      "epoch": 0.32674672358896695,
+      "eval_loss": 2.4128847122192383,
+      "eval_runtime": 53.1054,
+      "eval_samples_per_second": 94.152,
+      "eval_steps_per_second": 23.538,
+      "num_input_tokens_seen": 17956859456,
+      "step": 68500
+    },
+    {
+      "epoch": 0.32698522484706105,
+      "grad_norm": 0.15245509147644043,
+      "learning_rate": 2.6235218056235634e-05,
+      "loss": 2.5209,
+      "num_input_tokens_seen": 17969966656,
+      "step": 68550
+    },
+    {
+      "epoch": 0.3272237261051552,
+      "grad_norm": 0.15148235857486725,
+      "learning_rate": 2.4471741852423235e-05,
+      "loss": 2.5284,
+      "num_input_tokens_seen": 17983073856,
+      "step": 68600
+    },
+    {
+      "epoch": 0.3274622273632493,
+      "grad_norm": 0.15678688883781433,
+      "learning_rate": 2.276812823220964e-05,
+      "loss": 2.537,
+      "num_input_tokens_seen": 17996181056,
+      "step": 68650
+    },
+    {
+      "epoch": 0.3277007286213435,
+      "grad_norm": 0.15105360746383667,
+      "learning_rate": 2.1124591657534777e-05,
+      "loss": 2.5321,
+      "num_input_tokens_seen": 18009288256,
+      "step": 68700
+    },
+    {
+      "epoch": 0.32793922987943763,
+      "grad_norm": 0.15369552373886108,
+      "learning_rate": 1.9541339027450256e-05,
+      "loss": 2.5291,
+      "num_input_tokens_seen": 18022395456,
+      "step": 68750
+    },
+    {
+      "epoch": 0.32817773113753174,
+      "grad_norm": 0.1551530808210373,
+      "learning_rate": 1.801856965207338e-05,
+      "loss": 2.5201,
+      "num_input_tokens_seen": 18035502656,
+      "step": 68800
+    },
+    {
+      "epoch": 0.3284162323956259,
+      "grad_norm": 0.14859162271022797,
+      "learning_rate": 1.6556475227496815e-05,
+      "loss": 2.5436,
+      "num_input_tokens_seen": 18048609856,
+      "step": 68850
+    },
+    {
+      "epoch": 0.32865473365372,
+      "grad_norm": 0.14972691237926483,
+      "learning_rate": 1.5155239811656562e-05,
+      "loss": 2.5221,
+      "num_input_tokens_seen": 18061717056,
+      "step": 68900
+    },
+    {
+      "epoch": 0.32889323491181416,
+      "grad_norm": 0.156805619597435,
+      "learning_rate": 1.3815039801161721e-05,
+      "loss": 2.5248,
+      "num_input_tokens_seen": 18074824256,
+      "step": 68950
+    },
+    {
+      "epoch": 0.3291317361699083,
+      "grad_norm": 0.148334801197052,
+      "learning_rate": 1.2536043909088191e-05,
+      "loss": 2.5361,
+      "num_input_tokens_seen": 18087931456,
+      "step": 69000
+    },
+    {
+      "epoch": 0.3291317361699083,
+      "eval_loss": 2.4120428562164307,
+      "eval_runtime": 52.9258,
+      "eval_samples_per_second": 94.472,
+      "eval_steps_per_second": 23.618,
+      "num_input_tokens_seen": 18087931456,
+      "step": 69000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 17825787456,
+  "num_input_tokens_seen": 18087931456,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -12131,7 +12309,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.768572124165571e+18,
+  "total_flos": 4.838698202691011e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null