Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4faae999aae7bdb005e759f5800196dad8c366321f5757ffb0cd810595ad0722
+oid sha256:501fef97e868de2fe769f6afcc199fa4dcdcac6dc0d54a7fbfd43f4bcdb09305
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de6ec90481b17fdf0dbb66af6a33a218beab40180fd7766e682f67587ccf105
+oid sha256:94750ae2885a37a4bbc50a398a3ab56133a4ae66975744ebe68424cb12b41246
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f87b4e2959c3797be663a45d01659738f60369c9bf34bc2324a8a07e37c7d7e
+oid sha256:946bd86f101a9915666543051804c83e95356c740ad2bfc8b9b0bebcc0db0f88
 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": 0.020446279366951734,
+  "epoch": 0.030669419050427603,
   "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": 2.742,
       "eval_steps_per_second": 1.371,
       "step": 26
+    },
+    {
+      "epoch": 0.021232674727219108,
+      "grad_norm": 1.2242342233657837,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.6702,
+      "step": 27
+    },
+    {
+      "epoch": 0.022019070087486485,
+      "grad_norm": 1.7602314949035645,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.9246,
+      "step": 28
+    },
+    {
+      "epoch": 0.02280546544775386,
+      "grad_norm": 2.0709216594696045,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.8103,
+      "step": 29
+    },
+    {
+      "epoch": 0.023591860808021232,
+      "grad_norm": 1.5635908842086792,
+      "learning_rate": 5e-05,
+      "loss": 0.8027,
+      "step": 30
+    },
+    {
+      "epoch": 0.024378256168288606,
+      "grad_norm": 1.6824203729629517,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.776,
+      "step": 31
+    },
+    {
+      "epoch": 0.02516465152855598,
+      "grad_norm": 1.457542061805725,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.5255,
+      "step": 32
+    },
+    {
+      "epoch": 0.025951046888823357,
+      "grad_norm": 1.5966757535934448,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.6032,
+      "step": 33
+    },
+    {
+      "epoch": 0.02673744224909073,
+      "grad_norm": 1.5422358512878418,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.548,
+      "step": 34
+    },
+    {
+      "epoch": 0.027523837609358105,
+      "grad_norm": 1.623889446258545,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7702,
+      "step": 35
+    },
+    {
+      "epoch": 0.02831023296962548,
+      "grad_norm": 1.665121078491211,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.6063,
+      "step": 36
+    },
+    {
+      "epoch": 0.029096628329892852,
+      "grad_norm": 1.3971141576766968,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.48,
+      "step": 37
+    },
+    {
+      "epoch": 0.02988302369016023,
+      "grad_norm": 1.3747204542160034,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.6483,
+      "step": 38
+    },
+    {
+      "epoch": 0.030669419050427603,
+      "grad_norm": 1.3398278951644897,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.7969,
+      "step": 39
+    },
+    {
+      "epoch": 0.030669419050427603,
+      "eval_loss": 0.8240298628807068,
+      "eval_runtime": 792.48,
+      "eval_samples_per_second": 2.703,
+      "eval_steps_per_second": 1.351,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5951402720087245e+17,
+  "total_flos": 2.3927104080130867e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null