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:b23fa9aaf0155071ceaa66c9a8d8329dbc866cd6c8cc1368b7e23c5f53082851
+oid sha256:660c6c5e67778f682cc5383ee8378cd5ba9a597f047a6d261866ad2bd853bdf6
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d55f67d909c2d5e7c75923363a0582e63bbdad5fc59876aed12febc7f3f2f1
+oid sha256:23eff95c0d4a651a755f8a3da6b2293079ef8dcfff7673a29436ca22ff25862d
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd1f9f945d63f30a37dbb6e9479669c0d43f1dc4f315a3846d3a1bd7da9fa8f
+oid sha256:cb98ef5303ec81ed369a5e6d1fe97c66c7de85c1a6cadb74ab2fa30d5017f2f4
 size 14244

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": 0.016753926701570682,
+  "epoch": 0.025130890052356022,
   "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": 110.282,
       "eval_steps_per_second": 55.141,
       "step": 26
+    },
+    {
+      "epoch": 0.017398308497784936,
+      "grad_norm": 1.248848557472229,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 7.0013,
+      "step": 27
+    },
+    {
+      "epoch": 0.018042690293999193,
+      "grad_norm": 1.4550312757492065,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 7.6238,
+      "step": 28
+    },
+    {
+      "epoch": 0.01868707209021345,
+      "grad_norm": 2.163661241531372,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 8.13,
+      "step": 29
+    },
+    {
+      "epoch": 0.019331453886427707,
+      "grad_norm": 1.2935118675231934,
+      "learning_rate": 5e-05,
+      "loss": 7.4064,
+      "step": 30
+    },
+    {
+      "epoch": 0.019975835682641965,
+      "grad_norm": 1.2071995735168457,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 7.492,
+      "step": 31
+    },
+    {
+      "epoch": 0.020620217478856222,
+      "grad_norm": 1.0634459257125854,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 7.3088,
+      "step": 32
+    },
+    {
+      "epoch": 0.02126459927507048,
+      "grad_norm": 1.2333537340164185,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 7.4175,
+      "step": 33
+    },
+    {
+      "epoch": 0.021908981071284736,
+      "grad_norm": 1.3628766536712646,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 7.3945,
+      "step": 34
+    },
+    {
+      "epoch": 0.022553362867498993,
+      "grad_norm": 1.8400943279266357,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 7.7443,
+      "step": 35
+    },
+    {
+      "epoch": 0.02319774466371325,
+      "grad_norm": 1.8728278875350952,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 7.7232,
+      "step": 36
+    },
+    {
+      "epoch": 0.023842126459927507,
+      "grad_norm": 1.2013438940048218,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 7.6996,
+      "step": 37
+    },
+    {
+      "epoch": 0.024486508256141765,
+      "grad_norm": 2.287853240966797,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 7.2294,
+      "step": 38
+    },
+    {
+      "epoch": 0.025130890052356022,
+      "grad_norm": 1.4032453298568726,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 7.8582,
+      "step": 39
+    },
+    {
+      "epoch": 0.025130890052356022,
+      "eval_loss": 7.3332672119140625,
+      "eval_runtime": 23.6689,
+      "eval_samples_per_second": 110.44,
+      "eval_steps_per_second": 55.22,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 56606749360128.0,
+  "total_flos": 85113745440768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null