Training in progress, step 336, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c596eb13b8db82a68751a2138594214d39b07a147dd04547897055834b7d77
+oid sha256:ea066fdca2f0d275773ed066d4c455188e3952dfed554e671a608b38cc250b4e
 size 251748704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c20d3ae67c4bad639d556720d21185f76fc24607c15065edf053a9d3a78281fc
+oid sha256:b9186903cf8e60f4528473cb91735927a30f3724d2f5e201baca1780dd2f02a6
 size 128585300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2bf1bdfa144734acb5d72227059f4ea9d478824668c29b9c9f85d4fed5dd2fd
+oid sha256:c475e3f159a7a6b7db4096692ffabb002354d0e0a9b836f72d1b1b771c07c06e
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4304077ace11d9a73040105a12dccc14f1f6fa754ec7ec8ac8d56dd1b4fceb7
+oid sha256:38c5bda5cbd593f318d88385534de55f5cad7a66e07f24fe746d21530217d84d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:367493fa4c262bd150909d13b8a89c3a3001c29e61808156ddc90574a67d5755
+oid sha256:0f21ee3264ef1496cfabccd5daf1f9e671e4427793e35cae9284a7a9b77e826c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6426f051742b414e13c7752769ab4279db3e8e86e029cb1973fc3658432c9998
+oid sha256:b5807b07e9892aad8a97434973963ca3908019f2646d4a33c584472a428246c5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0316ab07671fffcd24f1d6dedeb5b41d6e5808ab64506af6cae3d569237843af
+oid sha256:73411ca8ec7e5959b18da4fe8d2de8084ec9d3eedda030beb9eadece4c950464
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0352112676056338,
+  "epoch": 1.1830985915492958,
   "eval_steps": 42,
-  "global_step": 294,
+  "global_step": 336,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,6 +757,112 @@
       "eval_samples_per_second": 57.034,
       "eval_steps_per_second": 1.789,
       "step": 294
+    },
+    {
+      "epoch": 1.045774647887324,
+      "grad_norm": 1.3563522100448608,
+      "learning_rate": 1.8349078860833123e-05,
+      "loss": 0.4868,
+      "step": 297
+    },
+    {
+      "epoch": 1.056338028169014,
+      "grad_norm": 1.4925919771194458,
+      "learning_rate": 1.7886810334224192e-05,
+      "loss": 0.4677,
+      "step": 300
+    },
+    {
+      "epoch": 1.0669014084507042,
+      "grad_norm": 1.559565544128418,
+      "learning_rate": 1.74271732938007e-05,
+      "loss": 0.4977,
+      "step": 303
+    },
+    {
+      "epoch": 1.0774647887323943,
+      "grad_norm": 1.6586874723434448,
+      "learning_rate": 1.6970337779808862e-05,
+      "loss": 0.4578,
+      "step": 306
+    },
+    {
+      "epoch": 1.0880281690140845,
+      "grad_norm": 1.4285913705825806,
+      "learning_rate": 1.6516472796085315e-05,
+      "loss": 0.4942,
+      "step": 309
+    },
+    {
+      "epoch": 1.0985915492957747,
+      "grad_norm": 1.3942043781280518,
+      "learning_rate": 1.6065746247534984e-05,
+      "loss": 0.4937,
+      "step": 312
+    },
+    {
+      "epoch": 1.1091549295774648,
+      "grad_norm": 1.3517378568649292,
+      "learning_rate": 1.561832487801565e-05,
+      "loss": 0.5066,
+      "step": 315
+    },
+    {
+      "epoch": 1.119718309859155,
+      "grad_norm": 1.447427749633789,
+      "learning_rate": 1.5174374208651912e-05,
+      "loss": 0.4476,
+      "step": 318
+    },
+    {
+      "epoch": 1.130281690140845,
+      "grad_norm": 1.5619040727615356,
+      "learning_rate": 1.4734058476601553e-05,
+      "loss": 0.4542,
+      "step": 321
+    },
+    {
+      "epoch": 1.1408450704225352,
+      "grad_norm": 1.5647931098937988,
+      "learning_rate": 1.4297540574296869e-05,
+      "loss": 0.4721,
+      "step": 324
+    },
+    {
+      "epoch": 1.1514084507042253,
+      "grad_norm": 1.5523713827133179,
+      "learning_rate": 1.386498198918352e-05,
+      "loss": 0.4627,
+      "step": 327
+    },
+    {
+      "epoch": 1.1619718309859155,
+      "grad_norm": 1.444485068321228,
+      "learning_rate": 1.3436542743979125e-05,
+      "loss": 0.4618,
+      "step": 330
+    },
+    {
+      "epoch": 1.1725352112676055,
+      "grad_norm": 1.5264121294021606,
+      "learning_rate": 1.3012381337473656e-05,
+      "loss": 0.465,
+      "step": 333
+    },
+    {
+      "epoch": 1.1830985915492958,
+      "grad_norm": 1.390081763267517,
+      "learning_rate": 1.2592654685893757e-05,
+      "loss": 0.4356,
+      "step": 336
+    },
+    {
+      "epoch": 1.1830985915492958,
+      "eval_loss": 0.13032591342926025,
+      "eval_runtime": 33.5427,
+      "eval_samples_per_second": 57.032,
+      "eval_steps_per_second": 1.789,
+      "step": 336
     }
   ],
   "logging_steps": 3,
@@ -776,7 +882,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4654876479806505e+18,
+  "total_flos": 2.8177001691207434e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null