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:d1a941435c1e53deba9d3cf0df4caa1ff2d82309a32178c4dd98d5edc34cb504
+oid sha256:c01167715fb1d023899a7563125550185a5d8366a83610d27eb314ab1b94109a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1590d44801fb5a95a9cd02e6d0ffb13c485bafec07a6e4f97b8484f8f3ca57d0
+oid sha256:5cec4842b08a985155952685fa293ab5342784bec7c494f61d6d31302d64a5d7
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3b6581f6b33326bbcd8b468d20a59b8114d7b1b656c310a34922fb317e9432
+oid sha256:da41f2039be1057494c712d703219c55068070b24135c38cd63d179d4ad50b11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016936521915859358,
+  "epoch": 0.0033873043831718717,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 9.336,
       "eval_steps_per_second": 4.668,
       "step": 25
+    },
+    {
+      "epoch": 0.0017613982792493734,
+      "grad_norm": 0.32836493849754333,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0067,
+      "step": 26
+    },
+    {
+      "epoch": 0.001829144366912811,
+      "grad_norm": 1.969914197921753,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0121,
+      "step": 27
+    },
+    {
+      "epoch": 0.0018968904545762482,
+      "grad_norm": 0.06996850669384003,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0007,
+      "step": 28
+    },
+    {
+      "epoch": 0.0019646365422396855,
+      "grad_norm": 0.19153662025928497,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.0068,
+      "step": 29
+    },
+    {
+      "epoch": 0.0020323826299031233,
+      "grad_norm": 0.3428010940551758,
+      "learning_rate": 5e-05,
+      "loss": 0.0103,
+      "step": 30
+    },
+    {
+      "epoch": 0.0020323826299031233,
+      "eval_loss": 0.014756828546524048,
+      "eval_runtime": 666.2233,
+      "eval_samples_per_second": 9.33,
+      "eval_steps_per_second": 4.665,
+      "step": 30
+    },
+    {
+      "epoch": 0.0021001287175665606,
+      "grad_norm": 1.1103867292404175,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0087,
+      "step": 31
+    },
+    {
+      "epoch": 0.002167874805229998,
+      "grad_norm": 4.091057300567627,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0299,
+      "step": 32
+    },
+    {
+      "epoch": 0.002235620892893435,
+      "grad_norm": 0.04187934845685959,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0009,
+      "step": 33
+    },
+    {
+      "epoch": 0.002303366980556873,
+      "grad_norm": 0.9004775285720825,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0088,
+      "step": 34
+    },
+    {
+      "epoch": 0.0023711130682203103,
+      "grad_norm": 0.049271903932094574,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0008,
+      "step": 35
+    },
+    {
+      "epoch": 0.0023711130682203103,
+      "eval_loss": 0.009419509209692478,
+      "eval_runtime": 666.5456,
+      "eval_samples_per_second": 9.326,
+      "eval_steps_per_second": 4.663,
+      "step": 35
+    },
+    {
+      "epoch": 0.0024388591558837476,
+      "grad_norm": 0.044682763516902924,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0009,
+      "step": 36
+    },
+    {
+      "epoch": 0.0025066052435471853,
+      "grad_norm": 0.013265944086015224,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0005,
+      "step": 37
+    },
+    {
+      "epoch": 0.0025743513312106226,
+      "grad_norm": 0.07124783098697662,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0011,
+      "step": 38
+    },
+    {
+      "epoch": 0.00264209741887406,
+      "grad_norm": 0.04415963962674141,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0008,
+      "step": 39
+    },
+    {
+      "epoch": 0.0027098435065374973,
+      "grad_norm": 0.45105212926864624,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0125,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027098435065374973,
+      "eval_loss": 0.010271004401147366,
+      "eval_runtime": 666.1075,
+      "eval_samples_per_second": 9.332,
+      "eval_steps_per_second": 4.666,
+      "step": 40
+    },
+    {
+      "epoch": 0.002777589594200935,
+      "grad_norm": 0.14058659970760345,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0009,
+      "step": 41
+    },
+    {
+      "epoch": 0.0028453356818643723,
+      "grad_norm": 0.008363386616110802,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0003,
+      "step": 42
+    },
+    {
+      "epoch": 0.0029130817695278096,
+      "grad_norm": 0.32420364022254944,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0076,
+      "step": 43
+    },
+    {
+      "epoch": 0.0029808278571912474,
+      "grad_norm": 0.9214268326759338,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0155,
+      "step": 44
+    },
+    {
+      "epoch": 0.0030485739448546847,
+      "grad_norm": 0.06376875936985016,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0052,
+      "step": 45
+    },
+    {
+      "epoch": 0.0030485739448546847,
+      "eval_loss": 0.009266946464776993,
+      "eval_runtime": 666.2551,
+      "eval_samples_per_second": 9.33,
+      "eval_steps_per_second": 4.665,
+      "step": 45
+    },
+    {
+      "epoch": 0.003116320032518122,
+      "grad_norm": 0.09901077300310135,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0007,
+      "step": 46
+    },
+    {
+      "epoch": 0.0031840661201815593,
+      "grad_norm": 0.04962729290127754,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.001,
+      "step": 47
+    },
+    {
+      "epoch": 0.003251812207844997,
+      "grad_norm": 0.09600146114826202,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0015,
+      "step": 48
+    },
+    {
+      "epoch": 0.0033195582955084344,
+      "grad_norm": 0.02424442768096924,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.0033873043831718717,
+      "grad_norm": 0.14273981750011444,
+      "learning_rate": 0.0,
+      "loss": 0.0054,
+      "step": 50
+    },
+    {
+      "epoch": 0.0033873043831718717,
+      "eval_loss": 0.009067730978131294,
+      "eval_runtime": 666.9516,
+      "eval_samples_per_second": 9.32,
+      "eval_steps_per_second": 4.66,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.86502613041152e+16,
+  "total_flos": 3.748702522127155e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null