Training in progress, step 2134, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4531cecc4e308a35dc907f81b5204f58f87403a6008584884dae9f8d5e3178ad
+oid sha256:2d13135869408c362410b6d65a9ecf14fcbec80f6a15aee0cf299eff51f090af
 size 735217848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41adcafe7f4fb36e8df90cb2a36c6fc9005eadf99b272fd5a69c8b1c71c58878
+oid sha256:d9a0b7a39de0aa8d9888d2f2710d48cfcf1e88b35f597dd289a68fd843ed1b1b
 size 1470521978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0886b5e6b4eb6c54d008834760837138a75d96ac8156628b1654cc847af0e990
+oid sha256:0e929bfb8d61dabc9ff9440d99be02b793be97dcf206c259cdc957e3702b21cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5146063efca63e5eea8f3db237a9d2214ab60b2b370c91142e2b5e596c8cc2ad
+oid sha256:0d9e4b230e7ad00add7adfd0d7846e7a79fb156cfc157db8c226ab66e3110285
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9372071227741331,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2134,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1727,6 +1727,113 @@
       "eval_spearman_manhattan": 0.7818782293686074,
       "eval_steps_per_second": 19.865,
       "step": 2000
+    },
+    {
+      "epoch": 0.9418931583880038,
+      "grad_norm": 1.3811417818069458,
+      "learning_rate": 8.822633552014996e-05,
+      "loss": 0.2759,
+      "step": 2010
+    },
+    {
+      "epoch": 0.9465791940018744,
+      "grad_norm": 2.8094141483306885,
+      "learning_rate": 8.816776007497658e-05,
+      "loss": 0.3046,
+      "step": 2020
+    },
+    {
+      "epoch": 0.9512652296157451,
+      "grad_norm": 1.8067703247070312,
+      "learning_rate": 8.810918462980319e-05,
+      "loss": 0.314,
+      "step": 2030
+    },
+    {
+      "epoch": 0.9559512652296157,
+      "grad_norm": 1.9540753364562988,
+      "learning_rate": 8.805060918462981e-05,
+      "loss": 0.2965,
+      "step": 2040
+    },
+    {
+      "epoch": 0.9606373008434864,
+      "grad_norm": 2.20998477935791,
+      "learning_rate": 8.799203373945643e-05,
+      "loss": 0.3278,
+      "step": 2050
+    },
+    {
+      "epoch": 0.9653233364573571,
+      "grad_norm": 2.156224250793457,
+      "learning_rate": 8.793345829428304e-05,
+      "loss": 0.3202,
+      "step": 2060
+    },
+    {
+      "epoch": 0.9700093720712277,
+      "grad_norm": 1.6349718570709229,
+      "learning_rate": 8.787488284910965e-05,
+      "loss": 0.3192,
+      "step": 2070
+    },
+    {
+      "epoch": 0.9746954076850984,
+      "grad_norm": 1.7507764101028442,
+      "learning_rate": 8.781630740393628e-05,
+      "loss": 0.3148,
+      "step": 2080
+    },
+    {
+      "epoch": 0.979381443298969,
+      "grad_norm": 1.6444741487503052,
+      "learning_rate": 8.77577319587629e-05,
+      "loss": 0.3009,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9840674789128397,
+      "grad_norm": 1.5341808795928955,
+      "learning_rate": 8.769915651358951e-05,
+      "loss": 0.3119,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9840674789128397,
+      "eval_loss": 0.04616248607635498,
+      "eval_pearson_cosine": 0.8028400286804569,
+      "eval_pearson_dot": 0.8142363636471543,
+      "eval_pearson_euclidean": 0.7825157658447595,
+      "eval_pearson_manhattan": 0.7827871893341012,
+      "eval_runtime": 4.9143,
+      "eval_samples_per_second": 305.23,
+      "eval_spearman_cosine": 0.805895283206979,
+      "eval_spearman_dot": 0.8167650665649905,
+      "eval_spearman_euclidean": 0.7880766458177777,
+      "eval_spearman_manhattan": 0.7880451603002018,
+      "eval_steps_per_second": 19.128,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9887535145267105,
+      "grad_norm": 2.1978578567504883,
+      "learning_rate": 8.764058106841613e-05,
+      "loss": 0.3473,
+      "step": 2110
+    },
+    {
+      "epoch": 0.993439550140581,
+      "grad_norm": 1.6111299991607666,
+      "learning_rate": 8.758200562324273e-05,
+      "loss": 0.2743,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9981255857544518,
+      "grad_norm": 2.0017919540405273,
+      "learning_rate": 8.752343017806935e-05,
+      "loss": 0.3201,
+      "step": 2130
     }
   ],
   "logging_steps": 10,
@@ -1741,7 +1848,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }