Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4403ef0b87240c588cc9018c851ca6def10f9c7117832646feb23b1a497b369
+oid sha256:07e15bec14df042e2e7eca6ffe7f64bcf3b886e37bb085e135041f610cfe2040
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be42a8ebdcc7133c1e8767042d17d85472064db7301c3d7d6fe198265028d741
+oid sha256:bffc36f8b3467c1d766cee5386960279c9cb758e1ca2413e1f2cfcef4458fc2a
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36686ab7aaf279855ae5edae6e8dd4b21ba79aa690f1c62e97aa173fa071ce13
+oid sha256:4cb349276f60d14bc86a47f7cc4b135102502e33556f3f2bbced9bf7c0933954
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16447368421052633,
+  "epoch": 0.32894736842105265,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 10.552,
       "eval_steps_per_second": 5.317,
       "step": 25
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 6.711698532104492,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 10.4598,
+      "step": 26
+    },
+    {
+      "epoch": 0.17763157894736842,
+      "grad_norm": 5.988046646118164,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 12.4122,
+      "step": 27
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 6.7396345138549805,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 10.6514,
+      "step": 28
+    },
+    {
+      "epoch": 0.19078947368421054,
+      "grad_norm": 7.260731220245361,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 10.9607,
+      "step": 29
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 6.341261863708496,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 12.1942,
+      "step": 30
+    },
+    {
+      "epoch": 0.20394736842105263,
+      "grad_norm": 7.080831527709961,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 13.2871,
+      "step": 31
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 9.200007438659668,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 11.3735,
+      "step": 32
+    },
+    {
+      "epoch": 0.21710526315789475,
+      "grad_norm": 8.438835144042969,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 9.7034,
+      "step": 33
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 8.435461044311523,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 12.39,
+      "step": 34
+    },
+    {
+      "epoch": 0.23026315789473684,
+      "grad_norm": 7.083141326904297,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 11.1461,
+      "step": 35
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 6.454171657562256,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 8.7345,
+      "step": 36
+    },
+    {
+      "epoch": 0.24342105263157895,
+      "grad_norm": 8.99131965637207,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 10.1263,
+      "step": 37
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 9.920761108398438,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 9.2578,
+      "step": 38
+    },
+    {
+      "epoch": 0.2565789473684211,
+      "grad_norm": 9.285501480102539,
+      "learning_rate": 5e-05,
+      "loss": 8.6679,
+      "step": 39
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 9.787482261657715,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 8.7731,
+      "step": 40
+    },
+    {
+      "epoch": 0.26973684210526316,
+      "grad_norm": 9.969244956970215,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 9.7417,
+      "step": 41
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 11.214414596557617,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.0999,
+      "step": 42
+    },
+    {
+      "epoch": 0.28289473684210525,
+      "grad_norm": 7.822074890136719,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.8718,
+      "step": 43
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 10.223742485046387,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 10.8404,
+      "step": 44
+    },
+    {
+      "epoch": 0.29605263157894735,
+      "grad_norm": 6.327630996704102,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.2936,
+      "step": 45
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 5.0185651779174805,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 8.2814,
+      "step": 46
+    },
+    {
+      "epoch": 0.3092105263157895,
+      "grad_norm": 5.958381175994873,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.0383,
+      "step": 47
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 5.123436450958252,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 12.5394,
+      "step": 48
+    },
+    {
+      "epoch": 0.3223684210526316,
+      "grad_norm": 5.286769866943359,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 10.9169,
+      "step": 49
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 5.482089042663574,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 11.8786,
+      "step": 50
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "eval_loss": 1.3653817176818848,
+      "eval_runtime": 12.2397,
+      "eval_samples_per_second": 10.54,
+      "eval_steps_per_second": 5.311,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.28694048489472e+16,
+  "total_flos": 6.57388096978944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null