Training in progress, step 34000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09d13e4122e8385a0b0d20fd5c3e0ad48906dae0b62b89359b90d5025d71342
+oid sha256:6a6b173b549e9d3319645826a9f24c43c83f85f0e4eb63106d17d813597efd32
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a1cf3d4f7ef91e1710cd1ff627ffe86cbcad4b359e09cfc0653ed1c67113f3
+oid sha256:318dc4beaeec065907f21b0996915041ab17bf3f8a094d80b20e22236127e478
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d470001272ba85c23801cee9a0e9047fab9ee4730b52f1c2aa2f87689e581d
+oid sha256:7b93f64c9a6269745acb7384d7354dcfadb94dacfa9ca2a2196b8150f90e2180
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:281c918d3dcf25df4f5a9bbf64a4fd88f0fa5c69087d3374f9f2ce6266f988a9
+oid sha256:14f558fa3ebdf8eded534006aef123b31a5895b4203fad741964c0be3f8e2ef2
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15741083034213005,
+  "epoch": 0.1621808555040128,
   "eval_steps": 500,
-  "global_step": 33000,
+  "global_step": 34000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5882,11 +5882,189 @@
       "eval_steps_per_second": 24.586,
       "num_input_tokens_seen": 8650752000,
       "step": 33000
+    },
+    {
+      "epoch": 0.15764933160022418,
+      "grad_norm": 0.2384626269340515,
+      "learning_rate": 0.001,
+      "loss": 2.6503,
+      "num_input_tokens_seen": 8663859200,
+      "step": 33050
+    },
+    {
+      "epoch": 0.15788783285831834,
+      "grad_norm": 0.18387843668460846,
+      "learning_rate": 0.001,
+      "loss": 2.6469,
+      "num_input_tokens_seen": 8676966400,
+      "step": 33100
+    },
+    {
+      "epoch": 0.15812633411641247,
+      "grad_norm": 0.23530641198158264,
+      "learning_rate": 0.001,
+      "loss": 2.6484,
+      "num_input_tokens_seen": 8690073600,
+      "step": 33150
+    },
+    {
+      "epoch": 0.1583648353745066,
+      "grad_norm": 0.2027565985918045,
+      "learning_rate": 0.001,
+      "loss": 2.6564,
+      "num_input_tokens_seen": 8703180800,
+      "step": 33200
+    },
+    {
+      "epoch": 0.15860333663260073,
+      "grad_norm": 0.21472220122814178,
+      "learning_rate": 0.001,
+      "loss": 2.6543,
+      "num_input_tokens_seen": 8716288000,
+      "step": 33250
+    },
+    {
+      "epoch": 0.15884183789069486,
+      "grad_norm": 0.19012615084648132,
+      "learning_rate": 0.001,
+      "loss": 2.6378,
+      "num_input_tokens_seen": 8729395200,
+      "step": 33300
+    },
+    {
+      "epoch": 0.159080339148789,
+      "grad_norm": 0.18018738925457,
+      "learning_rate": 0.001,
+      "loss": 2.6461,
+      "num_input_tokens_seen": 8742502400,
+      "step": 33350
+    },
+    {
+      "epoch": 0.15931884040688316,
+      "grad_norm": 0.20139184594154358,
+      "learning_rate": 0.001,
+      "loss": 2.6419,
+      "num_input_tokens_seen": 8755609600,
+      "step": 33400
+    },
+    {
+      "epoch": 0.1595573416649773,
+      "grad_norm": 0.20734767615795135,
+      "learning_rate": 0.001,
+      "loss": 2.6299,
+      "num_input_tokens_seen": 8768716800,
+      "step": 33450
+    },
+    {
+      "epoch": 0.15979584292307142,
+      "grad_norm": 0.18958640098571777,
+      "learning_rate": 0.001,
+      "loss": 2.6525,
+      "num_input_tokens_seen": 8781824000,
+      "step": 33500
+    },
+    {
+      "epoch": 0.15979584292307142,
+      "eval_loss": 2.5301430225372314,
+      "eval_runtime": 64.6928,
+      "eval_samples_per_second": 77.288,
+      "eval_steps_per_second": 19.322,
+      "num_input_tokens_seen": 8781824000,
+      "step": 33500
+    },
+    {
+      "epoch": 0.16003434418116555,
+      "grad_norm": 0.20421727001667023,
+      "learning_rate": 0.001,
+      "loss": 2.6445,
+      "num_input_tokens_seen": 8794931200,
+      "step": 33550
+    },
+    {
+      "epoch": 0.16027284543925968,
+      "grad_norm": 0.18347379565238953,
+      "learning_rate": 0.001,
+      "loss": 2.6525,
+      "num_input_tokens_seen": 8808038400,
+      "step": 33600
+    },
+    {
+      "epoch": 0.16051134669735384,
+      "grad_norm": 0.19450639188289642,
+      "learning_rate": 0.001,
+      "loss": 2.6356,
+      "num_input_tokens_seen": 8821145600,
+      "step": 33650
+    },
+    {
+      "epoch": 0.16074984795544797,
+      "grad_norm": 0.17953775823116302,
+      "learning_rate": 0.001,
+      "loss": 2.6424,
+      "num_input_tokens_seen": 8834252800,
+      "step": 33700
+    },
+    {
+      "epoch": 0.1609883492135421,
+      "grad_norm": 0.1990649551153183,
+      "learning_rate": 0.001,
+      "loss": 2.6608,
+      "num_input_tokens_seen": 8847360000,
+      "step": 33750
+    },
+    {
+      "epoch": 0.16122685047163623,
+      "grad_norm": 0.19343194365501404,
+      "learning_rate": 0.001,
+      "loss": 2.6604,
+      "num_input_tokens_seen": 8860467200,
+      "step": 33800
+    },
+    {
+      "epoch": 0.16146535172973037,
+      "grad_norm": 0.19385921955108643,
+      "learning_rate": 0.001,
+      "loss": 2.6354,
+      "num_input_tokens_seen": 8873574400,
+      "step": 33850
+    },
+    {
+      "epoch": 0.1617038529878245,
+      "grad_norm": 0.1828273981809616,
+      "learning_rate": 0.001,
+      "loss": 2.6578,
+      "num_input_tokens_seen": 8886681600,
+      "step": 33900
+    },
+    {
+      "epoch": 0.16194235424591866,
+      "grad_norm": 0.216063991189003,
+      "learning_rate": 0.001,
+      "loss": 2.6575,
+      "num_input_tokens_seen": 8899788800,
+      "step": 33950
+    },
+    {
+      "epoch": 0.1621808555040128,
+      "grad_norm": 0.20358648896217346,
+      "learning_rate": 0.001,
+      "loss": 2.6499,
+      "num_input_tokens_seen": 8912896000,
+      "step": 34000
+    },
+    {
+      "epoch": 0.1621808555040128,
+      "eval_loss": 2.5330910682678223,
+      "eval_runtime": 50.7961,
+      "eval_samples_per_second": 98.433,
+      "eval_steps_per_second": 24.608,
+      "num_input_tokens_seen": 8912896000,
+      "step": 34000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 8650752000,
+  "num_input_tokens_seen": 8912896000,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -5901,7 +6079,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.31416059133952e+18,
+  "total_flos": 2.38428666986496e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null