Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aaaa3767043d7191f3616a665f7f718731c4f35db95ba8202337817ce5b08cc
+oid sha256:57008faf63190f8174dfb04d3216ca794eaffc75e476534d10a9ae3045537cb5
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6d55d98f45053f2b49d414413e75ad74f4d6abad509ff201fded5c959ed1cb
+oid sha256:9b99efe6efb634203731c3d39f125e59b59d9474aa14774d34a9c3449775b23d
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad815b13748f0812b2c462c7875bd40ddeacdc04e731c652b9c37d93433fd8b5
+oid sha256:479fe09538278095a8c4e069a30f54fe9d7521e2679463ebf624ab30c74e4c92
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b3b6e0513508b2f7704990941df6bea2bf4affa5755515a34179dee0bab2583
+oid sha256:11cc71f24b6c2faec4b629f9a7f88ea4522316c75837efa3ca4ea0ae721f3b18
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc5898674bc4f45da9b739464b5d707558ec8cf04583a390664d54301591a56
+oid sha256:ddce0b6389c1ee588c5b47c3e3123bd2ca2091d1dc97d735b02d2d5d079b70ae
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78a289fff836c9fe8ff31714f873f03468b52254d4fb41bf51d14f0ef5bc1bf
+oid sha256:e1ef410be96e921201d70c9cdb498d5ddc574cb528e377f040f8d07cd60919ae
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3427592116538132,
+  "epoch": 0.6855184233076264,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 12.365,
       "eval_steps_per_second": 3.215,
       "step": 25
+    },
+    {
+      "epoch": 0.3564695801199657,
+      "grad_norm": 0.4161844551563263,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.859,
+      "step": 26
+    },
+    {
+      "epoch": 0.37017994858611825,
+      "grad_norm": 0.4057946801185608,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.8209,
+      "step": 27
+    },
+    {
+      "epoch": 0.3838903170522708,
+      "grad_norm": 0.45725005865097046,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8762,
+      "step": 28
+    },
+    {
+      "epoch": 0.3976006855184233,
+      "grad_norm": 0.5133175849914551,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.8786,
+      "step": 29
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.6212847232818604,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9259,
+      "step": 30
+    },
+    {
+      "epoch": 0.4250214224507284,
+      "grad_norm": 0.6563170552253723,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9841,
+      "step": 31
+    },
+    {
+      "epoch": 0.4387317909168809,
+      "grad_norm": 0.6918400526046753,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9366,
+      "step": 32
+    },
+    {
+      "epoch": 0.4524421593830334,
+      "grad_norm": 0.7071172595024109,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.9409,
+      "step": 33
+    },
+    {
+      "epoch": 0.4661525278491859,
+      "grad_norm": 0.9048558473587036,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.9652,
+      "step": 34
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 1.1677721738815308,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9168,
+      "step": 35
+    },
+    {
+      "epoch": 0.493573264781491,
+      "grad_norm": 2.0543811321258545,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0244,
+      "step": 36
+    },
+    {
+      "epoch": 0.5072836332476436,
+      "grad_norm": 1.9809794425964355,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.957,
+      "step": 37
+    },
+    {
+      "epoch": 0.5209940017137961,
+      "grad_norm": 0.4107670485973358,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9078,
+      "step": 38
+    },
+    {
+      "epoch": 0.5347043701799485,
+      "grad_norm": 0.2933681607246399,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8194,
+      "step": 39
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.3296855688095093,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7945,
+      "step": 40
+    },
+    {
+      "epoch": 0.5621251071122536,
+      "grad_norm": 0.36227262020111084,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.851,
+      "step": 41
+    },
+    {
+      "epoch": 0.5758354755784062,
+      "grad_norm": 0.4559353291988373,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.897,
+      "step": 42
+    },
+    {
+      "epoch": 0.5895458440445587,
+      "grad_norm": 0.45754337310791016,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8841,
+      "step": 43
+    },
+    {
+      "epoch": 0.6032562125107113,
+      "grad_norm": 0.5436176657676697,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.9113,
+      "step": 44
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.6519604325294495,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9513,
+      "step": 45
+    },
+    {
+      "epoch": 0.6306769494430163,
+      "grad_norm": 0.6538817286491394,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.9248,
+      "step": 46
+    },
+    {
+      "epoch": 0.6443873179091688,
+      "grad_norm": 0.8654205203056335,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.9545,
+      "step": 47
+    },
+    {
+      "epoch": 0.6580976863753213,
+      "grad_norm": 1.1048208475112915,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0274,
+      "step": 48
+    },
+    {
+      "epoch": 0.6718080548414739,
+      "grad_norm": 1.4500497579574585,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0133,
+      "step": 49
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 1.932473063468933,
+      "learning_rate": 1e-05,
+      "loss": 0.8543,
+      "step": 50
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "eval_loss": 0.9967225790023804,
+      "eval_runtime": 4.0537,
+      "eval_samples_per_second": 12.335,
+      "eval_steps_per_second": 3.207,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null