Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a1b6d87dc1fb270b46a64ac51ae0eb9fc677537735cfc5bf2f5fa946ab4142
+oid sha256:7d45b2c1b8953404021c16605d0de80ad936228c735cfdc030863eb91831aa3d
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66abdcbc9aabede0b74f3f4083c19a92c63f8d286830fecf31ba5d242d8b795e
+oid sha256:0a20dcb5e4784b182a9e3577482fb2fb9ab3a2eea4445e1c75e61ae5197019fe
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d535cf080674396fb72928f6111bb7f64589019b0899774b6c6db72a95e900e4
+oid sha256:185c4fed5976485f851475b83d32c75768629ff69422fd0d3d27a11ccafde888
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010239781551326906,
+  "epoch": 0.013653042068435874,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 42.028,
       "eval_steps_per_second": 21.014,
       "step": 150
+    },
+    {
+      "epoch": 0.010581107603037801,
+      "grad_norm": 2.8252055644989014,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 2.1986,
+      "step": 155
+    },
+    {
+      "epoch": 0.010922433654748698,
+      "grad_norm": 2.882528066635132,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 2.1574,
+      "step": 160
+    },
+    {
+      "epoch": 0.011263759706459596,
+      "grad_norm": 2.57167911529541,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 2.2536,
+      "step": 165
+    },
+    {
+      "epoch": 0.011605085758170493,
+      "grad_norm": 2.8177096843719482,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 2.1281,
+      "step": 170
+    },
+    {
+      "epoch": 0.01194641180988139,
+      "grad_norm": 2.2039341926574707,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 2.0143,
+      "step": 175
+    },
+    {
+      "epoch": 0.012287737861592285,
+      "grad_norm": 2.465358018875122,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 2.1856,
+      "step": 180
+    },
+    {
+      "epoch": 0.012629063913303182,
+      "grad_norm": 2.2475521564483643,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 2.1777,
+      "step": 185
+    },
+    {
+      "epoch": 0.01297038996501408,
+      "grad_norm": 2.3308393955230713,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 2.3441,
+      "step": 190
+    },
+    {
+      "epoch": 0.013311716016724977,
+      "grad_norm": 2.915706157684326,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 2.3743,
+      "step": 195
+    },
+    {
+      "epoch": 0.013653042068435874,
+      "grad_norm": 3.283146381378174,
+      "learning_rate": 0.0,
+      "loss": 2.1816,
+      "step": 200
+    },
+    {
+      "epoch": 0.013653042068435874,
+      "eval_loss": 2.2533507347106934,
+      "eval_runtime": 147.1216,
+      "eval_samples_per_second": 41.924,
+      "eval_steps_per_second": 20.962,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -263,12 +341,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7673759347507200.0,
+  "total_flos": 1.02316791300096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null