Training in progress, step 800, checkpoint

last-checkpoint/model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7402095373828868c6a8c82feed83c288050530180d57b6352e806cf58b1f6
+oid sha256:d74149d859635ddb3b8125743f520898c6ec4eb07cca13c578f3576bdfcec95d
 size 4840658560

last-checkpoint/model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f62da095bfe2f7bab3bc886fc3bc2b6de500f06f57f897eafb8dc0efb326fd8
+oid sha256:dfa0304220ec7858fdcb92598ed790d12dcd2c2a97794188cc51eead70167fd1
 size 4857206856

last-checkpoint/model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6b096a5676e65903cff59acf69d696927f6cc30a379206e9cf4eeece59d6d7a
+oid sha256:223bbf67180d65542f5fe74d87193e9559cdd780e59185fdc07feb5440f23f87
 size 4857206904

last-checkpoint/model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de37c4d3e07cda4c12efbb271b44e386d980542786ad5bd58846677dc3229213
+oid sha256:559933ab169a5ec4ca2cc1952bba17572c188fb2cb069e9921a817468ed399c5
 size 4857206904

last-checkpoint/model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64218f8c0e4a08ca5ebf894c332331d6e36968327167e22813cd4ea6e69a0e27
+oid sha256:8dd887b3c10513128153999ecdbeb08b8f55f80ffe947eedb06e7ac91272b59b
 size 4857206904

last-checkpoint/model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e551d45159d773a5d9a73c93ba8e731328c39b98762114a539357d30098dd964
+oid sha256:05198868838e96c5aff164a6595a25743dc877c7f7f4a03ad8360a047b083459
 size 2684734256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 1.6,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,126 @@
       "eval_samples_per_second": 68.926,
       "eval_steps_per_second": 3.535,
       "step": 400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.9651033878326416,
+      "learning_rate": 1.8e-05,
+      "loss": 0.7497,
+      "step": 450
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.6827173233032227,
+      "eval_runtime": 2.5909,
+      "eval_samples_per_second": 60.21,
+      "eval_steps_per_second": 3.088,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.7542426586151123,
+      "learning_rate": 2e-05,
+      "loss": 0.7622,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6903170347213745,
+      "eval_runtime": 2.4721,
+      "eval_samples_per_second": 63.105,
+      "eval_steps_per_second": 3.236,
+      "step": 500
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 2.384434938430786,
+      "learning_rate": 1.999390827019096e-05,
+      "loss": 0.484,
+      "step": 550
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 0.7237842679023743,
+      "eval_runtime": 2.9344,
+      "eval_samples_per_second": 53.162,
+      "eval_steps_per_second": 2.726,
+      "step": 550
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.1198794841766357,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.5145,
+      "step": 600
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.7352678179740906,
+      "eval_runtime": 3.8017,
+      "eval_samples_per_second": 41.034,
+      "eval_steps_per_second": 2.104,
+      "step": 600
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 6.234444618225098,
+      "learning_rate": 1.9945218953682736e-05,
+      "loss": 0.5093,
+      "step": 650
+    },
+    {
+      "epoch": 1.3,
+      "eval_loss": 0.7311124801635742,
+      "eval_runtime": 2.2672,
+      "eval_samples_per_second": 68.808,
+      "eval_steps_per_second": 3.529,
+      "step": 650
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.112931489944458,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.5248,
+      "step": 700
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.734488844871521,
+      "eval_runtime": 2.2746,
+      "eval_samples_per_second": 68.582,
+      "eval_steps_per_second": 3.517,
+      "step": 700
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.4556541442871094,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.5107,
+      "step": 750
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.723623514175415,
+      "eval_runtime": 2.256,
+      "eval_samples_per_second": 69.148,
+      "eval_steps_per_second": 3.546,
+      "step": 750
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.025707960128784,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.5171,
+      "step": 800
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.7228586077690125,
+      "eval_runtime": 2.2603,
+      "eval_samples_per_second": 69.016,
+      "eval_steps_per_second": 3.539,
+      "step": 800
     }
   ],
   "logging_steps": 50,
@@ -134,7 +254,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 400,
-  "total_flos": 1.9232917507014656e+16,
+  "total_flos": 3.860410960707584e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null