Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c8b974e314b98a2712368ee23c630ef3eb30ab969cdc8f8a7c3fba6de61d4f
+oid sha256:dedf215e9b506136c4eafaa5ca983fab54ed4eb2af03d61c3f95ec65d05da787
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7158c9f9ccd1ba85502b2bb2c5f9ec3f583780fa992ace238229391c1e323e63
+oid sha256:fa05fea595e28a91c765e7e95378a3f84bc9106fc2e6146f83186626bae9e711
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d920d35377b6218b0a182ca529dc7f210a3398080e4578011b7878234683794
+oid sha256:9e06dfbf969388fb27efc692631d298abe0d1c57738a0c64598fe664b1ac46b1
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7594d618d6ba19521c7abdc5d9c3d75c88e696a2ccaf3aad9e2ee70281ff7494
+oid sha256:77f6f8dca22790e21b49d4a3e5b2c2d34a14c2511eb61bf406f69b9611e05181
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04,
+  "epoch": 0.08,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,6 +166,164 @@
       "eval_samples_per_second": 295.612,
       "eval_steps_per_second": 18.58,
       "step": 2000
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 0.3338668942451477,
+      "learning_rate": 0.0009962330744753604,
+      "loss": 4.163348388671875,
+      "step": 2100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.25480538606643677,
+      "learning_rate": 0.0009958371593124988,
+      "loss": 4.118557434082032,
+      "step": 2200
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 0.2351720631122589,
+      "learning_rate": 0.0009954215513685335,
+      "loss": 4.1006707763671875,
+      "step": 2300
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.23063364624977112,
+      "learning_rate": 0.0009949862671498437,
+      "loss": 4.084933166503906,
+      "step": 2400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.270161896944046,
+      "learning_rate": 0.000994531323944276,
+      "loss": 4.043960876464844,
+      "step": 2500
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.23590487241744995,
+      "learning_rate": 0.0009940567398204583,
+      "loss": 4.043964233398437,
+      "step": 2600
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 0.2604995369911194,
+      "learning_rate": 0.000993562533627081,
+      "loss": 4.023601379394531,
+      "step": 2700
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.21301409602165222,
+      "learning_rate": 0.0009930487249921495,
+      "loss": 4.006760864257813,
+      "step": 2800
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 0.21575306355953217,
+      "learning_rate": 0.0009925153343222043,
+      "loss": 3.99057861328125,
+      "step": 2900
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2405770868062973,
+      "learning_rate": 0.00099196238280151,
+      "loss": 4.004396667480469,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.3194532243250246,
+      "eval_loss": 3.945106267929077,
+      "eval_runtime": 6.283,
+      "eval_samples_per_second": 308.927,
+      "eval_steps_per_second": 19.417,
+      "step": 3000
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 0.22380003333091736,
+      "learning_rate": 0.0009913898923912148,
+      "loss": 3.9952774047851562,
+      "step": 3100
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.21692751348018646,
+      "learning_rate": 0.0009907978858284775,
+      "loss": 3.9829229736328124,
+      "step": 3200
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 0.22457344830036163,
+      "learning_rate": 0.0009901863866255652,
+      "loss": 3.9637200927734373,
+      "step": 3300
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.20820939540863037,
+      "learning_rate": 0.0009895554190689191,
+      "loss": 3.930269470214844,
+      "step": 3400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.1961025595664978,
+      "learning_rate": 0.0009889050082181896,
+      "loss": 3.91483154296875,
+      "step": 3500
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.23347830772399902,
+      "learning_rate": 0.0009882351799052416,
+      "loss": 3.8973043823242186,
+      "step": 3600
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 0.21384640038013458,
+      "learning_rate": 0.0009875459607331285,
+      "loss": 3.9072760009765624,
+      "step": 3700
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.21380040049552917,
+      "learning_rate": 0.000986837378075035,
+      "loss": 3.8974929809570313,
+      "step": 3800
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 0.2199064940214157,
+      "learning_rate": 0.0009861094600731911,
+      "loss": 3.884527587890625,
+      "step": 3900
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.2245541661977768,
+      "learning_rate": 0.000985362235637753,
+      "loss": 3.863822021484375,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.3280885939521158,
+      "eval_loss": 3.8499362468719482,
+      "eval_runtime": 6.3172,
+      "eval_samples_per_second": 307.255,
+      "eval_steps_per_second": 19.312,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -185,7 +343,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.839921733632e+16,
+  "total_flos": 1.5679843467264e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null