Training in progress, step 153000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6742b674b0d53e2c3daed10497d7535a63d9e9f7f594d41925fa37702bc1094
+oid sha256:49e33340944bdfba019639a505fb829fbf58de481dcbd6bfa34260585e39bc82
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab29f7de023579ff77f6510ad0f7600d1dadaeaa609fc84656241739c587bc8
+oid sha256:ea0c2ad8c2577dec58bcf798facca9b484958ae7510c46df4fbc524b7011e74a
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10363df25df4a89f891174d636e331bcdc2893b7259219b00bec7140fc37ee6b
+oid sha256:2bb1d6d2c94dbd4fc1bf9d5756f17ab78e6ccfa57b4112f0c257527e9ee1e447
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae8b4289a05289ec5bdbf9ddf513572ea179aa9b7d8e7afc52b70d2964dfe0f
+oid sha256:6a693861125ab0b2f85599d0c1f06c209c17c8fe0c9515e61fbc5e32f352f900
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.338892347780364,
+  "epoch": 3.360858406101622,
   "eval_steps": 500,
-  "global_step": 152000,
+  "global_step": 153000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -27064,11 +27064,189 @@
       "eval_steps_per_second": 15.528,
       "num_input_tokens_seen": 85971046944,
       "step": 152000
+    },
+    {
+      "epoch": 3.339990650696427,
+      "grad_norm": 0.10089096426963806,
+      "learning_rate": 0.0001,
+      "loss": 2.3468,
+      "num_input_tokens_seen": 86023475744,
+      "step": 152050
+    },
+    {
+      "epoch": 3.34108895361249,
+      "grad_norm": 0.093196339905262,
+      "learning_rate": 0.0001,
+      "loss": 2.351,
+      "num_input_tokens_seen": 86075903552,
+      "step": 152100
+    },
+    {
+      "epoch": 3.3421872565285526,
+      "grad_norm": 0.09717004001140594,
+      "learning_rate": 0.0001,
+      "loss": 2.3486,
+      "num_input_tokens_seen": 86128331904,
+      "step": 152150
+    },
+    {
+      "epoch": 3.343285559444616,
+      "grad_norm": 0.09837143868207932,
+      "learning_rate": 0.0001,
+      "loss": 2.3424,
+      "num_input_tokens_seen": 86180760704,
+      "step": 152200
+    },
+    {
+      "epoch": 3.3443838623606785,
+      "grad_norm": 0.08969301730394363,
+      "learning_rate": 0.0001,
+      "loss": 2.355,
+      "num_input_tokens_seen": 86233189120,
+      "step": 152250
+    },
+    {
+      "epoch": 3.3454821652767412,
+      "grad_norm": 0.09237448871135712,
+      "learning_rate": 0.0001,
+      "loss": 2.3472,
+      "num_input_tokens_seen": 86285617920,
+      "step": 152300
+    },
+    {
+      "epoch": 3.3465804681928044,
+      "grad_norm": 0.08787325024604797,
+      "learning_rate": 0.0001,
+      "loss": 2.3456,
+      "num_input_tokens_seen": 86338046720,
+      "step": 152350
+    },
+    {
+      "epoch": 3.347678771108867,
+      "grad_norm": 0.0857023298740387,
+      "learning_rate": 0.0001,
+      "loss": 2.3511,
+      "num_input_tokens_seen": 86390472640,
+      "step": 152400
+    },
+    {
+      "epoch": 3.3487770740249303,
+      "grad_norm": 0.09470528364181519,
+      "learning_rate": 0.0001,
+      "loss": 2.3481,
+      "num_input_tokens_seen": 86442901440,
+      "step": 152450
+    },
+    {
+      "epoch": 3.349875376940993,
+      "grad_norm": 0.08560249954462051,
+      "learning_rate": 0.0001,
+      "loss": 2.3419,
+      "num_input_tokens_seen": 86495325760,
+      "step": 152500
+    },
+    {
+      "epoch": 3.349875376940993,
+      "eval_loss": 2.260103225708008,
+      "eval_runtime": 79.9152,
+      "eval_samples_per_second": 62.566,
+      "eval_steps_per_second": 15.642,
+      "num_input_tokens_seen": 86495325760,
+      "step": 152500
+    },
+    {
+      "epoch": 3.3509736798570557,
+      "grad_norm": 0.1033218502998352,
+      "learning_rate": 0.0001,
+      "loss": 2.3473,
+      "num_input_tokens_seen": 86547749728,
+      "step": 152550
+    },
+    {
+      "epoch": 3.352071982773119,
+      "grad_norm": 0.08745966106653214,
+      "learning_rate": 0.0001,
+      "loss": 2.3524,
+      "num_input_tokens_seen": 86600178048,
+      "step": 152600
+    },
+    {
+      "epoch": 3.3531702856891816,
+      "grad_norm": 0.08843880146741867,
+      "learning_rate": 0.0001,
+      "loss": 2.3467,
+      "num_input_tokens_seen": 86652604992,
+      "step": 152650
+    },
+    {
+      "epoch": 3.3542685886052444,
+      "grad_norm": 0.09221280366182327,
+      "learning_rate": 0.0001,
+      "loss": 2.3472,
+      "num_input_tokens_seen": 86705033792,
+      "step": 152700
+    },
+    {
+      "epoch": 3.3553668915213075,
+      "grad_norm": 0.09814682602882385,
+      "learning_rate": 0.0001,
+      "loss": 2.3482,
+      "num_input_tokens_seen": 86757462592,
+      "step": 152750
+    },
+    {
+      "epoch": 3.3564651944373702,
+      "grad_norm": 0.09335148334503174,
+      "learning_rate": 0.0001,
+      "loss": 2.3454,
+      "num_input_tokens_seen": 86809891392,
+      "step": 152800
+    },
+    {
+      "epoch": 3.357563497353433,
+      "grad_norm": 0.09705245494842529,
+      "learning_rate": 0.0001,
+      "loss": 2.351,
+      "num_input_tokens_seen": 86862320192,
+      "step": 152850
+    },
+    {
+      "epoch": 3.358661800269496,
+      "grad_norm": 0.09022082388401031,
+      "learning_rate": 0.0001,
+      "loss": 2.3474,
+      "num_input_tokens_seen": 86914748672,
+      "step": 152900
+    },
+    {
+      "epoch": 3.359760103185559,
+      "grad_norm": 0.09682248532772064,
+      "learning_rate": 0.0001,
+      "loss": 2.3424,
+      "num_input_tokens_seen": 86967177472,
+      "step": 152950
+    },
+    {
+      "epoch": 3.360858406101622,
+      "grad_norm": 0.092010997235775,
+      "learning_rate": 0.0001,
+      "loss": 2.3463,
+      "num_input_tokens_seen": 87019603744,
+      "step": 153000
+    },
+    {
+      "epoch": 3.360858406101622,
+      "eval_loss": 2.2600295543670654,
+      "eval_runtime": 80.7842,
+      "eval_samples_per_second": 61.893,
+      "eval_steps_per_second": 15.473,
+      "num_input_tokens_seen": 87019603744,
+      "step": 153000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 85971046944,
+  "num_input_tokens_seen": 87019603744,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -27083,7 +27261,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5215307197191743e+20,
+  "total_flos": 1.5400882625115718e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null