Training in progress, step 750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46362f87c9a61c05b35d0017fee94e615fca0a9b7944183e4fe55ba595828133
+oid sha256:d1c23281588fe7914d4d4f44fa96d1bebe41c212bf719c33b5fdf7b40eeecca6
 size 239135488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d24afbca3886cdf731f6d838b9a4156a014dec44c201e2985259be59fc1c82
+oid sha256:192b8e53e5187f343994adcd574d24d72b38e9908a8d4af0ec0e2eb7e0a4cf96
 size 478529298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2562493ee420bea042a2629099ab839a87ff45ebc5efa964141a21ffe350f4
+oid sha256:2586975e1d3b683969aff70c9424e21fce04e276125109d1dca17ca7667d0c91
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc27f6f3a634484ed89290f95b9dae37d8dd2743b63bc90bc3c4a747107d486
+oid sha256:2d9acb300ee3481a499d71232bda2cc6822a3d265890998459ac4ab1f2a7a58f
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.053511977195739746,
-  "best_model_checkpoint": "./output/checkpoint-600",
-  "epoch": 0.6048387096774194,
+  "best_metric": 0.05326759070158005,
+  "best_model_checkpoint": "./output/checkpoint-750",
+  "epoch": 0.7560483870967742,
   "eval_steps": 150,
-  "global_step": 600,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -459,6 +459,119 @@
       "eval_samples_per_second": 8.551,
       "eval_steps_per_second": 8.551,
       "step": 600
+    },
+    {
+      "epoch": 0.6149193548387096,
+      "grad_norm": 0.6630131006240845,
+      "learning_rate": 0.00012168849786010133,
+      "loss": 0.077,
+      "step": 610
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.16494181752204895,
+      "learning_rate": 0.00012155857852471433,
+      "loss": 0.1101,
+      "step": 620
+    },
+    {
+      "epoch": 0.6350806451612904,
+      "grad_norm": 0.9052111506462097,
+      "learning_rate": 0.0001214262315224808,
+      "loss": 0.1151,
+      "step": 630
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.7651068568229675,
+      "learning_rate": 0.00012129146229366766,
+      "loss": 0.1093,
+      "step": 640
+    },
+    {
+      "epoch": 0.655241935483871,
+      "grad_norm": 0.16763581335544586,
+      "learning_rate": 0.00012115427637811003,
+      "loss": 0.0711,
+      "step": 650
+    },
+    {
+      "epoch": 0.6653225806451613,
+      "grad_norm": 0.6529646515846252,
+      "learning_rate": 0.00012101467941498357,
+      "loss": 0.1042,
+      "step": 660
+    },
+    {
+      "epoch": 0.6754032258064516,
+      "grad_norm": 0.21442104876041412,
+      "learning_rate": 0.0001208726771425727,
+      "loss": 0.0624,
+      "step": 670
+    },
+    {
+      "epoch": 0.6854838709677419,
+      "grad_norm": 0.27069932222366333,
+      "learning_rate": 0.00012072827539803463,
+      "loss": 0.0808,
+      "step": 680
+    },
+    {
+      "epoch": 0.6955645161290323,
+      "grad_norm": 0.203572615981102,
+      "learning_rate": 0.00012058148011715949,
+      "loss": 0.0861,
+      "step": 690
+    },
+    {
+      "epoch": 0.7056451612903226,
+      "grad_norm": 0.18072012066841125,
+      "learning_rate": 0.00012043229733412636,
+      "loss": 0.053,
+      "step": 700
+    },
+    {
+      "epoch": 0.7157258064516129,
+      "grad_norm": 0.62689608335495,
+      "learning_rate": 0.0001202807331812551,
+      "loss": 0.0998,
+      "step": 710
+    },
+    {
+      "epoch": 0.7258064516129032,
+      "grad_norm": 0.14409402012825012,
+      "learning_rate": 0.00012012679388875441,
+      "loss": 0.0709,
+      "step": 720
+    },
+    {
+      "epoch": 0.7358870967741935,
+      "grad_norm": 0.17387409508228302,
+      "learning_rate": 0.00011997048578446568,
+      "loss": 0.1087,
+      "step": 730
+    },
+    {
+      "epoch": 0.7459677419354839,
+      "grad_norm": 0.6958820223808289,
+      "learning_rate": 0.00011981181529360282,
+      "loss": 0.1266,
+      "step": 740
+    },
+    {
+      "epoch": 0.7560483870967742,
+      "grad_norm": 0.6624193787574768,
+      "learning_rate": 0.00011965078893848828,
+      "loss": 0.1003,
+      "step": 750
+    },
+    {
+      "epoch": 0.7560483870967742,
+      "eval_loss": 0.05326759070158005,
+      "eval_runtime": 57.7375,
+      "eval_samples_per_second": 8.66,
+      "eval_steps_per_second": 8.66,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -478,7 +591,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.430349986663629e+16,
+  "total_flos": 6.769083236135731e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null