Training in progress, step 293, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25415934fdfa3428f4f41889a2fa89441b5f655bd7fe502d2cf6cd3c8d6afa60
+oid sha256:3ca4f81346c4a205bfa86521d2cc7347529e8152ac937a23b193446b34b2b5ce
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa7554e50de075413f94225e1e74082fbf2afd0ec4dee6f8b422e1946ba3c3c
-size 110419524
+oid sha256:db4eb8361ca82643c0122e00a4213a3136900910e6240dc31e7dc111566e0360
+size 110420100

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42505232d4595a4dee4b8b6821cb8648751f824dc2882a36322f5f24049aa1b6
+oid sha256:f5ccace4018646f69f77a1b4e0e02db9114e1ec574087ee510b605021cf2f2b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aafecfe0890bf44f024d5ca5f4aa05be62d4539c35a7a6a0fbffd0946c0f6117
+oid sha256:ca03dcea02ebb7ce4e6bdb5df204f257b1dddb62bce1032e09059a7c06338c09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5029940119760479,
+  "epoch": 1.0025662959794697,
   "eval_steps": 147,
-  "global_step": 147,
+  "global_step": 293,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -121,6 +121,111 @@
       "eval_samples_per_second": 18.518,
       "eval_steps_per_second": 1.166,
       "step": 147
+    },
+    {
+      "epoch": 0.5132591958939264,
+      "grad_norm": 1.189348578453064,
+      "learning_rate": 0.0002,
+      "loss": 2.3341,
+      "step": 150
+    },
+    {
+      "epoch": 0.5474764756201882,
+      "grad_norm": 1.0971434116363525,
+      "learning_rate": 0.0002,
+      "loss": 2.2627,
+      "step": 160
+    },
+    {
+      "epoch": 0.58169375534645,
+      "grad_norm": 1.0656123161315918,
+      "learning_rate": 0.0002,
+      "loss": 2.2739,
+      "step": 170
+    },
+    {
+      "epoch": 0.6159110350727117,
+      "grad_norm": 1.1617597341537476,
+      "learning_rate": 0.0002,
+      "loss": 2.2446,
+      "step": 180
+    },
+    {
+      "epoch": 0.6501283147989735,
+      "grad_norm": 1.1609177589416504,
+      "learning_rate": 0.0002,
+      "loss": 2.2269,
+      "step": 190
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "grad_norm": 1.0725802183151245,
+      "learning_rate": 0.0002,
+      "loss": 2.2471,
+      "step": 200
+    },
+    {
+      "epoch": 0.718562874251497,
+      "grad_norm": 1.1435920000076294,
+      "learning_rate": 0.0002,
+      "loss": 2.2892,
+      "step": 210
+    },
+    {
+      "epoch": 0.7527801539777588,
+      "grad_norm": 1.1242313385009766,
+      "learning_rate": 0.0002,
+      "loss": 2.2795,
+      "step": 220
+    },
+    {
+      "epoch": 0.7869974337040205,
+      "grad_norm": 1.0565266609191895,
+      "learning_rate": 0.0002,
+      "loss": 2.2515,
+      "step": 230
+    },
+    {
+      "epoch": 0.8212147134302823,
+      "grad_norm": 1.1212342977523804,
+      "learning_rate": 0.0002,
+      "loss": 2.2805,
+      "step": 240
+    },
+    {
+      "epoch": 0.8554319931565441,
+      "grad_norm": 1.124230146408081,
+      "learning_rate": 0.0002,
+      "loss": 2.2378,
+      "step": 250
+    },
+    {
+      "epoch": 0.8896492728828058,
+      "grad_norm": 1.0999276638031006,
+      "learning_rate": 0.0002,
+      "loss": 2.222,
+      "step": 260
+    },
+    {
+      "epoch": 0.9238665526090676,
+      "grad_norm": 1.1538196802139282,
+      "learning_rate": 0.0002,
+      "loss": 2.2267,
+      "step": 270
+    },
+    {
+      "epoch": 0.9580838323353293,
+      "grad_norm": 1.2899906635284424,
+      "learning_rate": 0.0002,
+      "loss": 2.2384,
+      "step": 280
+    },
+    {
+      "epoch": 0.9923011120615911,
+      "grad_norm": 1.3248995542526245,
+      "learning_rate": 0.0002,
+      "loss": 2.236,
+      "step": 290
     }
   ],
   "logging_steps": 10,
@@ -135,12 +240,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.4214208735556403e+17,
+  "total_flos": 4.826112117351383e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null