Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83dc4a29e9fad91afb04b519bb068889f5562fa8cb33f3105b8a5ebc63e375aa
+oid sha256:7d6589d8ccec56ae7cec491e45f338265163dfaa0514671c6886c318939ff16b
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d9b0a631533c00609f474655b03a16ae3902a7acc9767684d28ae4ebb97948a
+oid sha256:556e0e496c347bcacdc631fcc976d989f763173ce71a481c5e595eda55e7868c
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6216dc83f24b17415976279736a88142c79dbe0c54e5abb8dfeed35308a890c
+oid sha256:96337aceb721df4a39beff9244b65d1cc5d873c4c0a7c3c253f42ec95bd3c737
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd34f63e44f9069fae7082f243a54db35fc68a432ae6aa527241e906af3957c
+oid sha256:4da44b1e728628aca7953c36b51c1a8e86ff48e7b0510da4dad905b7baf90075
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9403c85bf61e63b29aa17f85d67574a6719cd35ddf4bafac4bd64d6b0f040e46
+oid sha256:90dbcef4627cf6dae532a9a8253b624934e88872fdcc33c4ca09154619960b47
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:813a3607511b244d531aecd7484e78d5c8539b61749ecd7598b1f17679fac19c
+oid sha256:dd8d65a02101282957e9ff4a7ca57ff66ccbed5b37662c0225e938e0c9443324
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3902439024390244,
+  "epoch": 0.5853658536585366,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 111.638,
       "eval_steps_per_second": 14.172,
       "step": 26
+    },
+    {
+      "epoch": 0.4052532833020638,
+      "grad_norm": 2.5209052562713623,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.7009,
+      "step": 27
+    },
+    {
+      "epoch": 0.4202626641651032,
+      "grad_norm": 2.8235585689544678,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.7067,
+      "step": 28
+    },
+    {
+      "epoch": 0.4352720450281426,
+      "grad_norm": 1.5787421464920044,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.707,
+      "step": 29
+    },
+    {
+      "epoch": 0.450281425891182,
+      "grad_norm": 3.7540314197540283,
+      "learning_rate": 5e-05,
+      "loss": 0.715,
+      "step": 30
+    },
+    {
+      "epoch": 0.4652908067542214,
+      "grad_norm": 3.978583574295044,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.7071,
+      "step": 31
+    },
+    {
+      "epoch": 0.4803001876172608,
+      "grad_norm": 1.993086338043213,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.6994,
+      "step": 32
+    },
+    {
+      "epoch": 0.49530956848030017,
+      "grad_norm": 3.182072639465332,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.7108,
+      "step": 33
+    },
+    {
+      "epoch": 0.5103189493433395,
+      "grad_norm": 1.1114157438278198,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6889,
+      "step": 34
+    },
+    {
+      "epoch": 0.525328330206379,
+      "grad_norm": 1.384256362915039,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7044,
+      "step": 35
+    },
+    {
+      "epoch": 0.5403377110694184,
+      "grad_norm": 3.324063777923584,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.7098,
+      "step": 36
+    },
+    {
+      "epoch": 0.5553470919324578,
+      "grad_norm": 2.3583667278289795,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.695,
+      "step": 37
+    },
+    {
+      "epoch": 0.5703564727954972,
+      "grad_norm": 1.7996037006378174,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.688,
+      "step": 38
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.9545679092407227,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.6888,
+      "step": 39
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "eval_loss": 0.6947711110115051,
+      "eval_runtime": 5.7325,
+      "eval_samples_per_second": 78.325,
+      "eval_steps_per_second": 9.943,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.999169891434496e+16,
+  "total_flos": 4.498754837151744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null