Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e5aa83ea314da30a6ec0a6ec269ff5cf39237d3466631877f4ba4181db862d3
+oid sha256:1cbeeecf5f33a8fe98f465a7ebe436fa13049f32a089a744575f64c982ba6f45
 size 471641972

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26cba81b64fd91075b5245eb0f07f97e602bdf0fb2c89db319fba234803a644a
+oid sha256:b6c6070216d6484067400562a6849b4c72f15f3f6816280335b442d080a2a835
 size 943408715

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47b49161b40289a196f0b323f09234647ca94a52a813ac8389a3c26b9e4065b1
+oid sha256:5ddef0af302d858629ee6e839c4c03676d7fb5e8ecf72e844bea591625e6c15a
 size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f743afad260d48a721280fb087e2db9d559da17786d4f25babaf33caec1409
+size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07aeb2ac6edabf9bd17bc37036b0bfcddb1f3b70b32195f555982e9c1e0b8fec
+oid sha256:4403fd940f71a33a8adb6adb7bfa8324a48799df328fceb42fc6cd308ce99323
 size 1465

last-checkpoint/trainer_state.json

@@ -1,193 +1,98 @@
 {
   "best_global_step": null,
-  "best_metric": Infinity,
+  "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25380710659898476,
-  "eval_steps": 1000,
-  "global_step": 2000,
+  "epoch": 0.10152026598309688,
+  "eval_steps": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0001269035532994924,
-      "grad_norm": 22.005727767944336,
+      "epoch": 0.00010152026598309688,
+      "grad_norm": 22.092256546020508,
       "learning_rate": 0.0,
-      "loss": 13.3757,
+      "loss": 13.7932,
       "step": 1
     },
     {
-      "epoch": 0.012690355329949238,
-      "grad_norm": 38.664306640625,
-      "learning_rate": 1.2563451776649746e-05,
-      "loss": 11.1669,
+      "epoch": 0.010152026598309688,
+      "grad_norm": 32.477996826171875,
+      "learning_rate": 2.008113590263692e-05,
+      "loss": 10.8313,
       "step": 100
     },
     {
-      "epoch": 0.025380710659898477,
-      "grad_norm": 25.380781173706055,
-      "learning_rate": 2.5253807106598986e-05,
-      "loss": 7.8049,
+      "epoch": 0.020304053196619376,
+      "grad_norm": 23.895782470703125,
+      "learning_rate": 4.036511156186613e-05,
+      "loss": 7.3668,
       "step": 200
     },
     {
-      "epoch": 0.03807106598984772,
-      "grad_norm": 25.609392166137695,
-      "learning_rate": 3.794416243654822e-05,
-      "loss": 6.6303,
+      "epoch": 0.030456079794929064,
+      "grad_norm": 20.44896697998047,
+      "learning_rate": 6.064908722109534e-05,
+      "loss": 5.9214,
       "step": 300
     },
     {
-      "epoch": 0.050761421319796954,
-      "grad_norm": 21.906394958496094,
-      "learning_rate": 5.063451776649747e-05,
-      "loss": 5.6649,
+      "epoch": 0.04060810639323875,
+      "grad_norm": 12.489410400390625,
+      "learning_rate": 8.093306288032456e-05,
+      "loss": 5.0598,
       "step": 400
     },
     {
-      "epoch": 0.06345177664974619,
-      "grad_norm": 13.918214797973633,
-      "learning_rate": 6.33248730964467e-05,
-      "loss": 4.9902,
+      "epoch": 0.05076013299154844,
+      "grad_norm": 11.84785270690918,
+      "learning_rate": 9.9935883735841e-05,
+      "loss": 4.5018,
       "step": 500
     },
     {
-      "epoch": 0.07614213197969544,
-      "grad_norm": 10.558023452758789,
-      "learning_rate": 7.601522842639595e-05,
-      "loss": 4.5313,
+      "epoch": 0.06091215958985813,
+      "grad_norm": 10.175586700439453,
+      "learning_rate": 9.886727933319086e-05,
+      "loss": 4.1055,
       "step": 600
     },
     {
-      "epoch": 0.08883248730964467,
-      "grad_norm": 9.60472297668457,
-      "learning_rate": 8.870558375634518e-05,
-      "loss": 4.2284,
+      "epoch": 0.07106418618816782,
+      "grad_norm": 8.461668014526367,
+      "learning_rate": 9.779867493054072e-05,
+      "loss": 3.813,
       "step": 700
     },
     {
-      "epoch": 0.10152284263959391,
-      "grad_norm": 10.893503189086914,
-      "learning_rate": 9.992652952177398e-05,
-      "loss": 3.9399,
+      "epoch": 0.0812162127864775,
+      "grad_norm": 8.445116996765137,
+      "learning_rate": 9.673007052789058e-05,
+      "loss": 3.6419,
       "step": 800
     },
     {
-      "epoch": 0.11421319796954314,
-      "grad_norm": 10.343321800231934,
-      "learning_rate": 9.92586160833556e-05,
-      "loss": 3.6866,
+      "epoch": 0.09136823938478719,
+      "grad_norm": 8.415114402770996,
+      "learning_rate": 9.566146612524043e-05,
+      "loss": 3.4315,
       "step": 900
     },
     {
-      "epoch": 0.12690355329949238,
-      "grad_norm": 10.732213020324707,
-      "learning_rate": 9.859070264493722e-05,
-      "loss": 3.5191,
+      "epoch": 0.10152026598309688,
+      "grad_norm": 8.78720760345459,
+      "learning_rate": 9.45928617225903e-05,
+      "loss": 3.3252,
       "step": 1000
-    },
-    {
-      "epoch": 0.12690355329949238,
-      "eval_loss": NaN,
-      "eval_runtime": 758.7504,
-      "eval_samples_per_second": 332.374,
-      "eval_steps_per_second": 41.547,
-      "step": 1000
-    },
-    {
-      "epoch": 0.13959390862944163,
-      "grad_norm": 8.010664939880371,
-      "learning_rate": 9.792278920651884e-05,
-      "loss": 3.4147,
-      "step": 1100
-    },
-    {
-      "epoch": 0.15228426395939088,
-      "grad_norm": 8.114327430725098,
-      "learning_rate": 9.725487576810046e-05,
-      "loss": 3.2962,
-      "step": 1200
-    },
-    {
-      "epoch": 0.1649746192893401,
-      "grad_norm": 7.225535869598389,
-      "learning_rate": 9.658696232968207e-05,
-      "loss": 3.1452,
-      "step": 1300
-    },
-    {
-      "epoch": 0.17766497461928935,
-      "grad_norm": 7.01926326751709,
-      "learning_rate": 9.591904889126369e-05,
-      "loss": 3.0837,
-      "step": 1400
-    },
-    {
-      "epoch": 0.19035532994923857,
-      "grad_norm": 8.998798370361328,
-      "learning_rate": 9.525113545284532e-05,
-      "loss": 3.011,
-      "step": 1500
-    },
-    {
-      "epoch": 0.20304568527918782,
-      "grad_norm": 9.184762954711914,
-      "learning_rate": 9.458322201442693e-05,
-      "loss": 2.9722,
-      "step": 1600
-    },
-    {
-      "epoch": 0.21573604060913706,
-      "grad_norm": 7.888009071350098,
-      "learning_rate": 9.391530857600855e-05,
-      "loss": 2.9282,
-      "step": 1700
-    },
-    {
-      "epoch": 0.22842639593908629,
-      "grad_norm": 8.22140884399414,
-      "learning_rate": 9.324739513759018e-05,
-      "loss": 2.8396,
-      "step": 1800
-    },
-    {
-      "epoch": 0.24111675126903553,
-      "grad_norm": 6.9004950523376465,
-      "learning_rate": 9.257948169917178e-05,
-      "loss": 2.7948,
-      "step": 1900
-    },
-    {
-      "epoch": 0.25380710659898476,
-      "grad_norm": 8.627703666687012,
-      "learning_rate": 9.191156826075342e-05,
-      "loss": 2.7533,
-      "step": 2000
-    },
-    {
-      "epoch": 0.25380710659898476,
-      "eval_loss": NaN,
-      "eval_runtime": 631.0573,
-      "eval_samples_per_second": 399.629,
-      "eval_steps_per_second": 49.954,
-      "step": 2000
     }
   ],
   "logging_steps": 100,
-  "max_steps": 15760,
+  "max_steps": 9851,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
-    "EarlyStoppingCallback": {
-      "args": {
-        "early_stopping_patience": 3,
-        "early_stopping_threshold": 0.0
-      },
-      "attributes": {
-        "early_stopping_patience_counter": 1
-      }
-    },
     "TrainerControl": {
       "args": {
         "should_epoch_stop": false,
@@ -199,7 +104,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1087545149735424.0,
+  "total_flos": 542589699999744.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d31271322373138a24b0926f70a31fa802fc9dad83a42bf09bcb1e65b34018c
-size 5841
+oid sha256:9f6d2140fda77ba220cd4e909f52c6a71604647d304e3a03f975d883e07d792e
+size 5905