Training in progress, step 27000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5bec1c908d3674f0271db365b68b65eba5fcb240a0cdef465444744537e1b2
+oid sha256:b55abcd2a89267e04c5dc4d6890be5cd51083ea26331bc0049c8cb798c0b2817
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11bfd45a2b9dbe2a73500711ce838dcbec4327e5390757e20fb5c745b36e7ec1
+oid sha256:9e9ea5ffc99fb85ec5b642b4ddb430150759191b1ea5e8fb7a5392dcecaef6d1
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4f94ed5b86c54ed9f04920c1d057728a5c151ee0d04fd210f18196febf93b7
+oid sha256:2c02dfe3855e4fc4d5677c85754decec4c9943b8de46688d5cac8a0ecd3c5105
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ced8856b9ff194699de7fca54070bd17a17efd31d5f5d4d7e4c8ff1ec712ca9
+oid sha256:5585e9833c9684d1dabff9cec651205ae9bf4f81ab2bb2b589702ce44919fbb3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12402065420895095,
+  "epoch": 0.1287906793708337,
   "eval_steps": 500,
-  "global_step": 26000,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4636,11 +4636,189 @@
       "eval_steps_per_second": 24.613,
       "num_input_tokens_seen": 6815744000,
       "step": 26000
+    },
+    {
+      "epoch": 0.1242591554670451,
+      "grad_norm": 0.18573056161403656,
+      "learning_rate": 0.001,
+      "loss": 2.6565,
+      "num_input_tokens_seen": 6828851200,
+      "step": 26050
+    },
+    {
+      "epoch": 0.12449765672513922,
+      "grad_norm": 0.19160890579223633,
+      "learning_rate": 0.001,
+      "loss": 2.6797,
+      "num_input_tokens_seen": 6841958400,
+      "step": 26100
+    },
+    {
+      "epoch": 0.12473615798323336,
+      "grad_norm": 0.18323373794555664,
+      "learning_rate": 0.001,
+      "loss": 2.6602,
+      "num_input_tokens_seen": 6855065600,
+      "step": 26150
+    },
+    {
+      "epoch": 0.1249746592413275,
+      "grad_norm": 0.17691807448863983,
+      "learning_rate": 0.001,
+      "loss": 2.6676,
+      "num_input_tokens_seen": 6868172800,
+      "step": 26200
+    },
+    {
+      "epoch": 0.12521316049942163,
+      "grad_norm": 0.20718660950660706,
+      "learning_rate": 0.001,
+      "loss": 2.6588,
+      "num_input_tokens_seen": 6881280000,
+      "step": 26250
+    },
+    {
+      "epoch": 0.12545166175751576,
+      "grad_norm": 0.17811058461666107,
+      "learning_rate": 0.001,
+      "loss": 2.6754,
+      "num_input_tokens_seen": 6894387200,
+      "step": 26300
+    },
+    {
+      "epoch": 0.1256901630156099,
+      "grad_norm": 0.17490555346012115,
+      "learning_rate": 0.001,
+      "loss": 2.6605,
+      "num_input_tokens_seen": 6907494400,
+      "step": 26350
+    },
+    {
+      "epoch": 0.12592866427370406,
+      "grad_norm": 0.17391368746757507,
+      "learning_rate": 0.001,
+      "loss": 2.684,
+      "num_input_tokens_seen": 6920601600,
+      "step": 26400
+    },
+    {
+      "epoch": 0.1261671655317982,
+      "grad_norm": 0.16951416432857513,
+      "learning_rate": 0.001,
+      "loss": 2.6685,
+      "num_input_tokens_seen": 6933708800,
+      "step": 26450
+    },
+    {
+      "epoch": 0.12640566678989232,
+      "grad_norm": 0.17574581503868103,
+      "learning_rate": 0.001,
+      "loss": 2.6665,
+      "num_input_tokens_seen": 6946816000,
+      "step": 26500
+    },
+    {
+      "epoch": 0.12640566678989232,
+      "eval_loss": 2.556109666824341,
+      "eval_runtime": 50.8743,
+      "eval_samples_per_second": 98.281,
+      "eval_steps_per_second": 24.57,
+      "num_input_tokens_seen": 6946816000,
+      "step": 26500
+    },
+    {
+      "epoch": 0.12664416804798645,
+      "grad_norm": 0.19910745322704315,
+      "learning_rate": 0.001,
+      "loss": 2.6755,
+      "num_input_tokens_seen": 6959923200,
+      "step": 26550
+    },
+    {
+      "epoch": 0.12688266930608058,
+      "grad_norm": 0.20141273736953735,
+      "learning_rate": 0.001,
+      "loss": 2.6798,
+      "num_input_tokens_seen": 6973030400,
+      "step": 26600
+    },
+    {
+      "epoch": 0.1271211705641747,
+      "grad_norm": 0.1732529103755951,
+      "learning_rate": 0.001,
+      "loss": 2.6606,
+      "num_input_tokens_seen": 6986137600,
+      "step": 26650
+    },
+    {
+      "epoch": 0.12735967182226887,
+      "grad_norm": 0.17546698451042175,
+      "learning_rate": 0.001,
+      "loss": 2.6717,
+      "num_input_tokens_seen": 6999244800,
+      "step": 26700
+    },
+    {
+      "epoch": 0.127598173080363,
+      "grad_norm": 0.2186097502708435,
+      "learning_rate": 0.001,
+      "loss": 2.6702,
+      "num_input_tokens_seen": 7012352000,
+      "step": 26750
+    },
+    {
+      "epoch": 0.12783667433845713,
+      "grad_norm": 0.1735202819108963,
+      "learning_rate": 0.001,
+      "loss": 2.6795,
+      "num_input_tokens_seen": 7025459200,
+      "step": 26800
+    },
+    {
+      "epoch": 0.12807517559655127,
+      "grad_norm": 0.40701860189437866,
+      "learning_rate": 0.001,
+      "loss": 2.6591,
+      "num_input_tokens_seen": 7038566400,
+      "step": 26850
+    },
+    {
+      "epoch": 0.1283136768546454,
+      "grad_norm": 0.19710049033164978,
+      "learning_rate": 0.001,
+      "loss": 2.6841,
+      "num_input_tokens_seen": 7051673600,
+      "step": 26900
+    },
+    {
+      "epoch": 0.12855217811273956,
+      "grad_norm": 0.18638554215431213,
+      "learning_rate": 0.001,
+      "loss": 2.6718,
+      "num_input_tokens_seen": 7064780800,
+      "step": 26950
+    },
+    {
+      "epoch": 0.1287906793708337,
+      "grad_norm": 0.17546561360359192,
+      "learning_rate": 0.001,
+      "loss": 2.6547,
+      "num_input_tokens_seen": 7077888000,
+      "step": 27000
+    },
+    {
+      "epoch": 0.1287906793708337,
+      "eval_loss": 2.551922559738159,
+      "eval_runtime": 50.1864,
+      "eval_samples_per_second": 99.629,
+      "eval_steps_per_second": 24.907,
+      "num_input_tokens_seen": 7077888000,
+      "step": 27000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 6815744000,
+  "num_input_tokens_seen": 7077888000,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -4655,7 +4833,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.82327804166144e+18,
+  "total_flos": 1.89340412018688e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null