Training in progress, step 252, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd409d2cda44386875e2237cbc14387320bb7b2b55cde3c8ddd45a9c2bb03e9a
+oid sha256:586fd04ed04d760d37f53f41e09542570cc554ebc66067372543dd3f2a963511
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8061481dc5236ca996649ca5cc63afee81ef7df75bdd47d238714a9ba6b4f2
+oid sha256:28b2ceac6018dae6fdb4d9ef0f5c8fb480f407b18c678ebe83cbb5b4ab5cb5b7
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46bf71438827f27fea3a358fd83e1761732ffba0ae573ca96fc80e490196bc32
+oid sha256:29b9fe7e09a65746829ba365c53904d26ac9041437bdc46c4d9bdaea8de869a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd95a1db0e917ddf11b12a343f06e907fcec4b81104002e2471b4778587b465
+oid sha256:ee19ddad9c4c375a1de2d74fb4c1cf5e15d36c1ed47a2cb80f7cb0fbacb3b29e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6840390879478827,
+  "epoch": 0.8208469055374593,
   "eval_steps": 42,
-  "global_step": 210,
+  "global_step": 252,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -545,6 +545,112 @@
       "eval_samples_per_second": 23.348,
       "eval_steps_per_second": 5.871,
       "step": 210
+    },
+    {
+      "epoch": 0.6938110749185668,
+      "grad_norm": 2.490628719329834,
+      "learning_rate": 6.330184227833376e-05,
+      "loss": 1.4418,
+      "step": 213
+    },
+    {
+      "epoch": 0.7035830618892508,
+      "grad_norm": 2.3577187061309814,
+      "learning_rate": 6.237238428024572e-05,
+      "loss": 1.2653,
+      "step": 216
+    },
+    {
+      "epoch": 0.7133550488599348,
+      "grad_norm": 2.6168723106384277,
+      "learning_rate": 6.143834918526527e-05,
+      "loss": 1.4725,
+      "step": 219
+    },
+    {
+      "epoch": 0.7231270358306189,
+      "grad_norm": 2.343191146850586,
+      "learning_rate": 6.0500082534642464e-05,
+      "loss": 1.3543,
+      "step": 222
+    },
+    {
+      "epoch": 0.7328990228013029,
+      "grad_norm": 2.482631206512451,
+      "learning_rate": 5.955793143506863e-05,
+      "loss": 1.3523,
+      "step": 225
+    },
+    {
+      "epoch": 0.742671009771987,
+      "grad_norm": 2.1662986278533936,
+      "learning_rate": 5.861224443026595e-05,
+      "loss": 1.2848,
+      "step": 228
+    },
+    {
+      "epoch": 0.752442996742671,
+      "grad_norm": 2.496674060821533,
+      "learning_rate": 5.766337137204579e-05,
+      "loss": 1.3919,
+      "step": 231
+    },
+    {
+      "epoch": 0.762214983713355,
+      "grad_norm": 2.5266311168670654,
+      "learning_rate": 5.6711663290882776e-05,
+      "loss": 1.4481,
+      "step": 234
+    },
+    {
+      "epoch": 0.7719869706840391,
+      "grad_norm": 2.154391288757324,
+      "learning_rate": 5.575747226605298e-05,
+      "loss": 1.1874,
+      "step": 237
+    },
+    {
+      "epoch": 0.7817589576547231,
+      "grad_norm": 2.2282350063323975,
+      "learning_rate": 5.480115129538409e-05,
+      "loss": 1.2684,
+      "step": 240
+    },
+    {
+      "epoch": 0.7915309446254072,
+      "grad_norm": 2.377781391143799,
+      "learning_rate": 5.384305416466584e-05,
+      "loss": 1.2627,
+      "step": 243
+    },
+    {
+      "epoch": 0.8013029315960912,
+      "grad_norm": 2.505831480026245,
+      "learning_rate": 5.288353531676873e-05,
+      "loss": 1.2982,
+      "step": 246
+    },
+    {
+      "epoch": 0.8110749185667753,
+      "grad_norm": 2.424248456954956,
+      "learning_rate": 5.192294972051992e-05,
+      "loss": 1.2661,
+      "step": 249
+    },
+    {
+      "epoch": 0.8208469055374593,
+      "grad_norm": 2.3504350185394287,
+      "learning_rate": 5.0961652739384356e-05,
+      "loss": 1.3146,
+      "step": 252
+    },
+    {
+      "epoch": 0.8208469055374593,
+      "eval_loss": 1.3527233600616455,
+      "eval_runtime": 22.1769,
+      "eval_samples_per_second": 23.313,
+      "eval_steps_per_second": 5.862,
+      "step": 252
     }
   ],
   "logging_steps": 3,
@@ -564,7 +670,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5839392576831488e+17,
+  "total_flos": 1.9007271092197786e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null