Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e5d3d936d61547de24d6afdedcf2eb488a4bf314f425838eea7153c34cda3f
+oid sha256:4d4578ea45525b754cb730822b4b5e19895f177b38e0a8204f0f0d2d34a3d2c2
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8608210c82922ba0100ffea37c432c2407655c0eaa5dc9daa411a0234cb329
+oid sha256:c252f56184e8af807bdd63c3b61b4ad344e01d2c51768cbb39510437a12c6e36
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5feb56512e955691dc9bb9a1e37b9dd590e06a961d7d94560b679e2730b03194
+oid sha256:037d13720220086c05f76f1146cd4356e8b9d075b5d306338df00d366045e1c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf3f988e8fed2daa2e801eb1f19b681872781cf57f0fb7b896e859a12cfe2bb
+oid sha256:6f4c00d522bdde510099aafe1617b13d114dce17a17b44e05876f016f4e4d7af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7959539294242859,
-  "best_model_checkpoint": "./output/checkpoint-150",
-  "epoch": 6.521739130434782,
+  "best_metric": 0.7313653230667114,
+  "best_model_checkpoint": "./output/checkpoint-300",
+  "epoch": 13.043478260869565,
   "eval_steps": 150,
-  "global_step": 150,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -152,6 +152,151 @@
       "eval_samples_per_second": 22.618,
       "eval_steps_per_second": 22.618,
       "step": 150
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 1.5320531129837036,
+      "learning_rate": 2.9999892980750297e-05,
+      "loss": 0.6585,
+      "step": 160
+    },
+    {
+      "epoch": 7.391304347826087,
+      "grad_norm": 1.346379041671753,
+      "learning_rate": 2.9999854334972675e-05,
+      "loss": 0.7392,
+      "step": 170
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 1.726070761680603,
+      "learning_rate": 2.999980974373204e-05,
+      "loss": 0.7292,
+      "step": 180
+    },
+    {
+      "epoch": 8.26086956521739,
+      "grad_norm": 1.5403681993484497,
+      "learning_rate": 2.9999759207046075e-05,
+      "loss": 0.6246,
+      "step": 190
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 1.7414804697036743,
+      "learning_rate": 2.9999702724934804e-05,
+      "loss": 0.6765,
+      "step": 200
+    },
+    {
+      "epoch": 9.130434782608695,
+      "grad_norm": 1.0415966510772705,
+      "learning_rate": 2.999964029742062e-05,
+      "loss": 0.652,
+      "step": 210
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 1.2198948860168457,
+      "learning_rate": 2.9999571924528263e-05,
+      "loss": 0.5593,
+      "step": 220
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.529250979423523,
+      "learning_rate": 2.9999497606284837e-05,
+      "loss": 0.756,
+      "step": 230
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 1.4208300113677979,
+      "learning_rate": 2.9999417342719796e-05,
+      "loss": 0.7117,
+      "step": 240
+    },
+    {
+      "epoch": 10.869565217391305,
+      "grad_norm": 0.974891722202301,
+      "learning_rate": 2.9999331133864956e-05,
+      "loss": 0.5896,
+      "step": 250
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 1.1935385465621948,
+      "learning_rate": 2.9999238979754485e-05,
+      "loss": 0.6548,
+      "step": 260
+    },
+    {
+      "epoch": 11.73913043478261,
+      "grad_norm": 1.0492814779281616,
+      "learning_rate": 2.999914088042492e-05,
+      "loss": 0.6473,
+      "step": 270
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 1.3129431009292603,
+      "learning_rate": 2.9999036835915132e-05,
+      "loss": 0.5941,
+      "step": 280
+    },
+    {
+      "epoch": 12.608695652173914,
+      "grad_norm": 1.0831547975540161,
+      "learning_rate": 2.9998926846266365e-05,
+      "loss": 0.6329,
+      "step": 290
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 1.3950847387313843,
+      "learning_rate": 2.9998810911522213e-05,
+      "loss": 0.5809,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7313653230667114,
+      "eval_runtime": 0.4017,
+      "eval_samples_per_second": 24.891,
+      "eval_steps_per_second": 24.891,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.8609360456466675,
+      "eval_runtime": 0.4064,
+      "eval_samples_per_second": 24.603,
+      "eval_steps_per_second": 24.603,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7313653230667114,
+      "eval_runtime": 0.3955,
+      "eval_samples_per_second": 25.286,
+      "eval_steps_per_second": 25.286,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7757944464683533,
+      "eval_runtime": 0.396,
+      "eval_samples_per_second": 25.25,
+      "eval_steps_per_second": 25.25,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.8611125946044922,
+      "eval_runtime": 0.4025,
+      "eval_samples_per_second": 24.847,
+      "eval_steps_per_second": 24.847,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -171,7 +316,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3894839614291968.0,
+  "total_flos": 7724643094462464.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null