Model save

README.md

@@ -37,7 +37,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1.0
+- num_epochs: 3.0
 
 ### Training results
 

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 1.0,
+    "eval_gen_len": 78.04093919325707,
+    "eval_loss": 1.0967354774475098,
+    "eval_rouge1": 9.6103,
+    "eval_rouge2": 3.2602,
+    "eval_rougeL": 9.4833,
+    "eval_rougeLsum": 9.5204,
+    "eval_runtime": 305.3578,
+    "eval_samples": 1661,
+    "eval_samples_per_second": 5.44,
+    "eval_steps_per_second": 1.362,
+    "train_loss": 1.3809210790793738,
+    "train_runtime": 2386.364,
+    "train_samples": 14964,
+    "train_samples_per_second": 6.271,
+    "train_steps_per_second": 1.568
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_gen_len": 78.04093919325707,
+    "eval_loss": 1.0967354774475098,
+    "eval_rouge1": 9.6103,
+    "eval_rouge2": 3.2602,
+    "eval_rougeL": 9.4833,
+    "eval_rougeLsum": 9.5204,
+    "eval_runtime": 305.3578,
+    "eval_samples": 1661,
+    "eval_samples_per_second": 5.44,
+    "eval_steps_per_second": 1.362
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bae4afa9bf5bb83be9a38178940dcf2775cf77982f65053cc50e9602640236
+oid sha256:37846d11c8151954bf5997b55c431a0d3e59a1f8018b9c208ebb8eed603b171c
 size 2444578688

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.3809210790793738,
+    "train_runtime": 2386.364,
+    "train_samples": 14964,
+    "train_samples_per_second": 6.271,
+    "train_steps_per_second": 1.568
+}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3741,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.331729484095162e-05,
+      "loss": 1.7279,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.663458968190324e-05,
+      "loss": 1.5155,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.995188452285485e-05,
+      "loss": 1.4301,
+      "step": 1500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.326917936380647e-05,
+      "loss": 1.3448,
+      "step": 2000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.658647420475809e-05,
+      "loss": 1.2982,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.903769045709705e-06,
+      "loss": 1.2323,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.2210638866613206e-06,
+      "loss": 1.2036,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "step": 3741,
+      "total_flos": 1.70456184471552e+16,
+      "train_loss": 1.3809210790793738,
+      "train_runtime": 2386.364,
+      "train_samples_per_second": 6.271,
+      "train_steps_per_second": 1.568
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3741,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.70456184471552e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:191e6dd6c64f1d8a756f39b792c6ac1d4a0ad0ac14a860442ab3caad7f6f679f
+oid sha256:9fea473a216aa9aa4b033031c9e8f1485df505e03a5b11e6cee03b585b064ee7
 size 5048